Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    negative monetary values or financial loss indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Ranges of numbers, often with a hyphen

    np_acts-logits-general · gemini-2.0-flash

    numerical ranges and approximations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.45
     reloadData
    -0.40
     auri
    -0.40
    ftagPool
    -0.40
    adás
    -0.39
    ✨:
    -0.39
     aufge
    -0.38
    Geplaatst
    -0.38
     nakalista
    -0.36
    ThroughAttribute
    -0.36
    POSITIVE LOGITS
    awtextra
    0.69
     až
    0.56
    OrEqual
    0.55
     approximately
    0.52
    ximately
    0.52
     ranging
    0.50
    DIPSETTING
    0.50
     aproximado
    0.49
    帖最后由
    0.49
     roughly
    0.49
    Act Density 0.401%

    No Known Activations