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

    Neuronpedia

    INDEX
    Explanations

    C code accessing struct members via pointers and array indexing

    oai_token-act-pair · gemini-2.0-flash

    C code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.53
    DIPSETTING
    -0.53
     at
    -0.52
     onFailure
    -0.51
    (
    -0.50
    RegistryLite
    -0.49
    RepeatedField
    -0.47
    _{-\
    -0.47
     Smith
    -0.47
    ArrowToggle
    -0.47
    POSITIVE LOGITS
    ISupport
    0.59
    RTGC
    0.56
     écoute
    0.56
     ujednoznacz
    0.54
    ználat
    0.54
     morceau
    0.53
     contaba
    0.52
     للاسماء
    0.51
    almaz
    0.50
     NACA
    0.50
    Act Density 3.159%

    No Known Activations