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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >L
    -0.07
    ]",↵
    -0.07
    _validate
    -0.07
    ┋
    -0.07
    同等
    -0.07
    .methods
    -0.07
    京城
    -0.07
    各行各业
    -0.07
    _INTERFACE
    -0.06
    ∉
    -0.06
    POSITIVE LOGITS
    ::*
    0.07
    dato
    0.07
    Cha
    0.07
     '?
    0.07
    стой
    0.06
    Responsive
    0.06
    Interstitial
    0.06
     Oczywiście
    0.06
    _),
    0.06
    问题
    0.06
    Act Density 0.001%

    No Known Activations