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

    Neuronpedia

    INDEX
    Explanations

    code / programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     searcher
    -0.07
    rightarrow
    -0.06
     remember
    -0.06
    plemented
    -0.06
    ollection
    -0.06
    сі
    -0.06
    รค
    -0.06
    集合
    -0.06
    .auto
    -0.06
    .truth
    -0.06
    POSITIVE LOGITS
     Зап
    0.07
     Wein
    0.07
    に向
    0.06
     Под
    0.06
     Geld
    0.06
     вида
    0.06
    ERS
    0.06
     menn
    0.06
     Coron
    0.06
    BOUND
    0.06
    Act Density 0.000%

    No Known Activations