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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    090
    -0.08
    φέ
    -0.07
    央
    -0.07
     canonical
    -0.06
    598
    -0.06
     watershed
    -0.06
    数
    -0.06
    ferences
    -0.06
    ernity
    -0.06
    Ral
    -0.06
    POSITIVE LOGITS
    (aux
    0.08
     WHAT
    0.07
    .DataGridViewCellStyle
    0.07
     siti
    0.06
    aga
    0.06
     Whatever
    0.06
    .writeValue
    0.06
     ego
    0.06
     beau
    0.06
    =<?=$
    0.06
    Act Density 0.003%

    No Known Activations