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

    Neuronpedia

    INDEX
    Explanations

    href

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     рамках
    -0.07
    כתב
    -0.07
    jq
    -0.07
    .w
    -0.07
    Composer
    -0.07
    �
    -0.07
     maneuvers
    -0.06
    낯
    -0.06
     Chanel
    -0.06
    후
    -0.06
    POSITIVE LOGITS
     seis
    0.08
    =password
    0.07
    _SETTINGS
    0.07
    公众号
    0.07
    jie
    0.07
    🆔
    0.07
    گ
    0.07
    的表现
    0.07
    大多数
    0.07
    _management
    0.07
    Act Density 0.000%

    No Known Activations