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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hall
    -0.07
     právě
    -0.06
     Ved
    -0.06
    (pos
    -0.06
    eceği
    -0.06
     Sets
    -0.06
    hap
    -0.06
    _virtual
    -0.06
    Exp
    -0.06
    Hall
    -0.06
    POSITIVE LOGITS
    ोस
    0.07
     ges
    0.07
    [];↵
    0.07
    :number
    0.06
    ॉफ
    0.06
    .Small
    0.06
    ("/")
    0.06
     kdy
    0.06
     shirts
    0.06
    ())↵↵↵
    0.06
    Act Density 0.002%

    No Known Activations