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

    Neuronpedia

    INDEX
    Explanations

    forall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fatt
    -0.07
    _sector
    -0.07
     Butler
    -0.06
    	open
    -0.06
     already
    -0.06
    _ber
    -0.06
     harmless
    -0.06
     ar
    -0.06
     Sem
    -0.06
     gridColumn
    -0.06
    POSITIVE LOGITS
    forall
    0.10
    стан
    0.07
     içindeki
    0.07
    inent
    0.07
    comma
    0.07
    isí
    0.06
     Assassin
    0.06
    =current
    0.06
    руш
    0.06
    dto
    0.06
    Act Density 0.004%

    No Known Activations