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

    Neuronpedia

    INDEX
    Explanations

    stained glass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (`${
    -0.07
    当然
    -0.07
    Ź
    -0.07
     accru
    -0.06
     sincerity
    -0.06
     aims
    -0.06
     lock
    -0.06
    ьян
    -0.06
     atom
    -0.06
    (this
    -0.06
    POSITIVE LOGITS
    UPDATE
    0.08
    .addEdge
    0.07
    öyle
    0.06
     Euro
    0.06
     kötü
    0.06
    羕
    0.06
    endimento
    0.06
    ово
    0.06
    เทศกาล
    0.06
    市委书记
    0.06
    Act Density 0.007%

    No Known Activations