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

    Neuronpedia

    INDEX
    Explanations

    non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     psychology
    -0.07
     THAT
    -0.07
    言
    -0.07
    奄
    -0.07
    烟草
    -0.07
    想了
    -0.07
    Discovery
    -0.07
     fünf
    -0.07
    ysql
    -0.07
    bon
    -0.06
    POSITIVE LOGITS
    ик
    0.07
    姱
    0.07
    .c
    0.07
    亥
    0.07
    _get
    0.07
    _picker
    0.07
    님
    0.07
    Registr
    0.07
     deut
    0.07
    ul
    0.07
    Act Density 0.030%

    No Known Activations