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

    Neuronpedia

    INDEX
    Explanations

    letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    服务水平
    -0.07
     mappedBy
    -0.07
    seudo
    -0.07
    .synthetic
    -0.07
    席执行官
    -0.07
    -makers
    -0.07
     Erot
    -0.07
    _SHA
    -0.07
    Advisor
    -0.06
    :p
    -0.06
    POSITIVE LOGITS
     저는
    0.08
     confinement
    0.07
     donner
    0.07
     stab
    0.07
    ﾗ
    0.07
    ��
    0.07
    LAB
    0.06
     souvent
    0.06
     simplement
    0.06
     ahora
    0.06
    Act Density 0.001%

    No Known Activations