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

    Neuronpedia

    INDEX
    Explanations

    Democratic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.08
    	JOptionPane
    -0.07
     soc
    -0.07
     glBind
    -0.07
    dz
    -0.07
     nik
    -0.07
    	glBind
    -0.07
    ropical
    -0.06
     Lucky
    -0.06
     detalle
    -0.06
    POSITIVE LOGITS
    ウェ
    0.07
    acts
    0.07
    _SITE
    0.07
    �
    0.07
    mant
    0.07
    مار
    0.07
    าร
    0.07
    تان
    0.06
    立场
    0.06
    励
    0.06
    Act Density 0.007%

    No Known Activations