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

    Neuronpedia

    INDEX
    Explanations

    individual stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    邊
    -0.06
     μη
    -0.06
    .ap
    -0.06
     Perspective
    -0.06
    ANTE
    -0.06
    ante
    -0.06
    Animator
    -0.06
    _Module
    -0.06
    ú
    -0.06
     prostitutes
    -0.05
    POSITIVE LOGITS
     defended
    0.07
    cantidad
    0.07
    量
    0.07
    盤
    0.07
     behaves
    0.07
     Rangers
    0.07
     bufferSize
    0.06
     Namespace
    0.06
     settling
    0.06
    antom
    0.06
    Act Density 0.079%

    No Known Activations