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

    Neuronpedia

    INDEX
    Explanations

    ish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compilers
    -0.07
    .white
    -0.06
     sweating
    -0.06
     depart
    -0.06
     kissed
    -0.06
     mı
    -0.06
    _EQUALS
    -0.06
    Lv
    -0.06
     nao
    -0.06
     Dao
    -0.06
    POSITIVE LOGITS
    /weather
    0.07
    ponsible
    0.07
    .nz
    0.07
    decorate
    0.06
     Garrett
    0.06
     Danny
    0.06
    finding
    0.06
     Newfoundland
    0.06
    ज़
    0.06
     Norway
    0.06
    Act Density 0.001%

    No Known Activations