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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enerima
    -0.07
     //!
    -0.06
    dde
    -0.06
    -mon
    -0.06
    impan
    -0.06
    cw
    -0.06
     Saras
    -0.06
     Gap
    -0.06
    rıca
    -0.06
    忍
    -0.06
    POSITIVE LOGITS
    ﾟ
    0.07
     outlook
    0.06
    liste
    0.06
    gers
    0.06
     tela
    0.06
     Shard
    0.06
    Increase
    0.06
     Excellent
    0.06
    .gc
    0.06
     graceful
    0.06
    Act Density 0.002%

    No Known Activations