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

    Neuronpedia

    INDEX
    Explanations

    code/notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stellar
    -0.08
     wahr
    -0.08
     **
    -0.08
    ิง
    -0.08
    stellar
    -0.07
     ICS
    -0.07
    alert
    -0.07
    _PENDING
    -0.07
     gal
    -0.07
    -0.07
    POSITIVE LOGITS
     coils
    0.10
     стру
    0.10
     transmissions
    0.09
    .sock
    0.09
     Transmission
    0.09
    针
    0.09
    Transmission
    0.09
    іння
    0.09
     coil
    0.09
     consigli
    0.08
    Act Density 0.009%

    No Known Activations