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

    Neuronpedia

    INDEX
    Explanations

    batch size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insan
    -0.08
    via
    -0.07
     Sit
    -0.06
     savory
    -0.06
    _binary
    -0.06
    .setX
    -0.06
    .enums
    -0.06
    .handle
    -0.06
    major
    -0.06
    감
    -0.06
    POSITIVE LOGITS
     Arth
    0.07
    ']
↵
    0.06
     степени
    0.06
     *=
    0.06
     �
    0.06
    式会社
    0.06
     Dangerous
    0.06
     Sha
    0.06
     Ud
    0.06
    ADX
    0.06
    Act Density 0.010%

    No Known Activations