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

    Neuronpedia

    INDEX
    Explanations

    Transfer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    喇
    -0.07
    xmin
    -0.07
     önüne
    -0.07
    שום
    -0.07
    rowse
    -0.07
    mentation
    -0.07
    Lord
    -0.07
    _requirements
    -0.07
    _compute
    -0.07
     vrou
    -0.06
    POSITIVE LOGITS
    tero
    0.07
    فعاليات
    0.07
    zept
    0.07
    /helpers
    0.07
     }]);↵
    0.07
     stairs
    0.07
     ()=>
    0.06
    白天
    0.06
    庆典
    0.06
     ;↵
    0.06
    Act Density 0.001%

    No Known Activations