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

    Neuronpedia

    INDEX
    Explanations

    c

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flowing
    -0.06
    _warning
    -0.06
    ooting
    -0.06
     giản
    -0.06
     вероят
    -0.06
     اگر
    -0.06
    )
↵
↵
    -0.06
    Away
    -0.06
    Lista
    -0.06
     بدان
    -0.06
    POSITIVE LOGITS
    ween
    0.07
    SESSION
    0.07
     đảng
    0.06
    놓
    0.06
    ˘
    0.06
     ох
    0.06
     vai
    0.06
    @Column
    0.06
     sé
    0.06
    ковые
    0.06
    Act Density 0.004%

    No Known Activations