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

    Neuronpedia

    INDEX
    Explanations

    via

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ohne
    -0.07
    Frozen
    -0.07
    �인
    -0.07
    inventory
    -0.06
     droits
    -0.06
     Stanley
    -0.06
     зв
    -0.06
     anymore
    -0.06
     coer
    -0.06
     امام
    -0.06
    POSITIVE LOGITS
     via
    0.08
    )::
    0.08
     devise
    0.07
    yl
    0.07
    Via
    0.07
    viso
    0.07
     accommodations
    0.06
     Partisi
    0.06
    ussia
    0.06
     Via
    0.06
    Act Density 0.004%

    No Known Activations