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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    à
    -0.08
    ees
    -0.07
    ossier
    -0.07
    νη
    -0.07
    AYS
    -0.07
    ZH
    -0.07
     favourable
    -0.07
    	answer
    -0.06
     Huck
    -0.06
    ifestyle
    -0.06
    POSITIVE LOGITS
    _EM
    0.06
     mal
    0.06
     GLES
    0.06
    QualifiedName
    0.06
    очного
    0.06
     pi
    0.06
     الوطني
    0.06
     ">↵
    0.06
     selectable
    0.06
     сер
    0.05
    Act Density 0.017%

    No Known Activations