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

    Neuronpedia

    INDEX
    Explanations

    clauses with a subject followed by some form of "to be" or "begin" followed by "to"

    oai_token-act-pair · gemini-2.0-flash

    beginning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    antaranya
    -0.64
     kaynağından
    -0.63
    UrlResolution
    -0.62
     ब्रेकडाउन
    -0.59
    WireFormatLite
    -0.59
     AssemblyTitle
    -0.56
    beginning
    -0.54
     począ
    -0.54
     newBuilder
    -0.53
    began
    -0.52
    POSITIVE LOGITS
    ReusableCell
    0.58
     bed
    0.50
    iibo
    0.48
    rungsseite
    0.47
     involve
    0.45
    __':
    0.44
    Copyright
    0.44
    cesa
    0.43
    '):
    0.43
     ${({
    0.43
    Act Density 1.244%

    No Known Activations