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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     QApplication
    -0.06
    .samples
    -0.06
     rains
    -0.06
    tte
    -0.06
     før
    -0.06
    breaking
    -0.06
    .Char
    -0.06
    outed
    -0.06
    로그램
    -0.06
    archy
    -0.06
    POSITIVE LOGITS
    였
    0.07
     endure
    0.07
    렸
    0.07
     —
    0.06
     milyar
    0.06
    关系
    0.06
    렇
    0.06
     "",
    0.06
     widespread
    0.06
     т
    0.06
    Act Density 0.000%

    No Known Activations