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

    Neuronpedia

    INDEX
    Explanations

    Mathematical conditions and assumptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ortalama
    -0.07
    src
    -0.06
    .money
    -0.06
    _machine
    -0.06
     увелич
    -0.06
    _tgt
    -0.06
    請
    -0.06
    .Val
    -0.06
     num
    -0.06
     جوان
    -0.06
    POSITIVE LOGITS
     waters
    0.06
    undi
    0.06
    /**/*.
    0.06
    keeping
    0.06
     guts
    0.06
     bietet
    0.06
    -ranked
    0.06
    WR
    0.06
    �다
    0.06
     supplying
    0.06
    Act Density 0.007%

    No Known Activations