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

    Neuronpedia

    INDEX
    Explanations

    think

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     First
    -0.07
     pret
    -0.07
    first
    -0.07
     onclick
    -0.06
     licz
    -0.06
    First
    -0.06
     một
    -0.06
    _net
    -0.06
     guru
    -0.06
    13
    -0.06
    POSITIVE LOGITS
    HU
    0.07
     cesty
    0.07
     Claud
    0.07
     SubLObject
    0.06
    (@"%@",
    0.06
     olmadan
    0.06
     відч
    0.06
    ób
    0.06
    _Check
    0.06
     Müdürlüğü
    0.06
    Act Density 0.018%

    No Known Activations