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

    Neuronpedia

    INDEX
    Explanations

    configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alc
    -0.07
     Society
    -0.06
    /all
    -0.06
     detachment
    -0.06
    цький
    -0.06
     Nazi
    -0.06
     tốt
    -0.06
    .getConnection
    -0.06
    _OBJECT
    -0.06
    Charsets
    -0.06
    POSITIVE LOGITS
    establish
    0.07
    аб
    0.06
     disb
    0.06
    once
    0.06
     prefer
    0.06
     �
    0.06
    PLETED
    0.06
    Canceled
    0.06
    loses
    0.06
     perce
    0.06
    Act Density 0.026%

    No Known Activations