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

    Neuronpedia

    INDEX
    Explanations

    technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Spatial
    -0.07
    17
    -0.07
    亜
    -0.07
     words
    -0.07
     museum
    -0.06
    Nil
    -0.06
     元
    -0.06
    参加
    -0.06
    19
    -0.06
     thư
    -0.06
    POSITIVE LOGITS
     Liter
    0.06
     Porn
    0.06
    _WARNINGS
    0.06
    >";
↵
    0.06
     Unsafe
    0.06
     国家
    0.06
    Popular
    0.06
     inversion
    0.06
     TouchableOpacity
    0.06
    charg
    0.06
    Act Density 0.065%

    No Known Activations