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

    Neuronpedia

    INDEX
    Explanations

    code snippets and coding language keywords

    oai_token-act-pair · gemini-2.0-flash

    plus sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     .
    -0.72
     sèche
    -0.58
     gång
    -0.56
     gestes
    -0.56
    SourceChecksum
    -0.55
    TabIndex
    -0.55
     supérieurs
    -0.54
     militaires
    -0.52
     sidan
    -0.51
     sogni
    -0.51
    POSITIVE LOGITS
     +
    1.49
     $+$
    1.31
     $+
    1.24
    +
    1.20
     $+\
    1.20
     +
    1.16
    +</
    1.15
    ＋
    1.09
     + 
    1.09
     +\
    1.08
    Act Density 2.172%

    No Known Activations