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

    Neuronpedia

    INDEX
    Explanations

    before, experienced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PTH
    -0.07
     برق
    -0.06
    램
    -0.06
     února
    -0.06
    删除成功
    -0.06
    automatic
    -0.06
     Takım
    -0.06
     معدن
    -0.06
     cũng
    -0.06
    _da
    -0.06
    POSITIVE LOGITS
     �
    0.07
    內
    0.07
     Hawks
    0.07
     constituents
    0.07
     hallmark
    0.07
     (?)
    0.06
     Psychology
    0.06
     salute
    0.06
    “She
    0.06
    .ERR
    0.06
    Act Density 0.010%

    No Known Activations