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

    Neuronpedia

    INDEX
    Explanations

    amb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cih
    -0.07
     Hag
    -0.07
     resistance
    -0.06
     laws
    -0.06
    (dis
    -0.06
     ksi
    -0.06
     emulation
    -0.06
     Origins
    -0.06
    PropertyName
    -0.06
    族自治
    -0.06
    POSITIVE LOGITS
    PM
    0.07
    PS
    0.07
    मन
    0.06
    KE
    0.06
    KEEP
    0.06
    ิม
    0.06
    BA
    0.06
    _window
    0.06
    MQ
    0.06
    993
    0.06
    Act Density 0.001%

    No Known Activations