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

    Neuronpedia

    INDEX
    Explanations

    english stop words and punctuation contained within sentences

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —
    -0.54
     (
    -0.49
    –
    -0.44
    ry
    -0.42
     arv
    -0.40
    --
    -0.39
    ()]
    -0.39
    -(
    -0.39
    ε
    -0.39
    бой
    -0.38
    POSITIVE LOGITS
    writeFieldEnd
    0.92
     lenker
    0.88
    AndEndTag
    0.85
    StructEnd
    0.83
     Efq
    0.82
    rungsseite
    0.81
     isInitialized
    0.81
    AutoScaleMode
    0.80
    TemporalType
    0.78
     RouterModule
    0.77
    Act Density 2.051%

    No Known Activations