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

    Neuronpedia

    INDEX
    Explanations

    k

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    練
    -0.08
    Entre
    -0.07
    以上学历
    -0.07
    Miami
    -0.07
    .layers
    -0.07
    샵
    -0.07
     Efficiency
    -0.07
     stride
    -0.07
    浆
    -0.07
     Femme
    -0.07
    POSITIVE LOGITS
    k
    0.11
    𝗸
    0.09
    K
    0.09
    uk
    0.09
    ک
    0.09
    ᡴ
    0.09
    kü
    0.09
    ก
    0.09
    ak
    0.08
    vak
    0.08
    Act Density 0.646%

    No Known Activations