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

    Neuronpedia

    INDEX
    Explanations

    continuous states or actions related to belief and ongoing processes

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

    time and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.63
     autorytatywna
    -0.57
     يتيمه
    -0.53
    还不
    -0.49
     faſt
    -0.48
     pinulongan
    -0.48
    ſelves
    -0.46
     bientôt
    -0.46
     Sekarang
    -0.45
    ormais
    -0.44
    POSITIVE LOGITS
    ⤹
    0.52
    ">//
    0.46
    transQ
    0.42
    paksa
    0.42
    قایناق‌لار
    0.40
    ]=>
    0.39
    Scénario
    0.37
    ufc
    0.37
    цена
    0.37
    brite
    0.37
    Act Density 0.254%

    No Known Activations