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

    Neuronpedia

    INDEX
    Explanations

    instances of empty or whitespace sequences

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

    programming code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.65
    ंदीखरीदारी
    -0.61
    Халык
    -0.55
    ViewFeatures
    -0.49
     AssemblyCulture
    -0.48
    AutoScaleMode
    -0.47
    #
    -0.46
     ProtoMessage
    -0.43
     linkovi
    -0.43
     Infórmanos
    -0.42
    POSITIVE LOGITS
     tuổi
    0.43
    fence
    0.42
    IGENCE
    0.42
     useNavigate
    0.40
    ——–
    0.39
     LORD
    0.39
    Lord
    0.39
     Nasty
    0.39
    lope
    0.39
    emplar
    0.39
    Act Density 0.040%

    No Known Activations