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

    Neuronpedia

    INDEX
    Explanations

    =>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	inst
    -0.07
    	ctrl
    -0.07
     preg
    -0.07
     Hob
    -0.07
    	args
    -0.06
     adore
    -0.06
    AppDelegate
    -0.06
     ευ
    -0.06
    _BS
    -0.06
    $params
    -0.06
    POSITIVE LOGITS
    AccessorType
    0.06
    یش
    0.06
    ように
    0.06
    象
    0.06
    вав
    0.06
    ывает
    0.06
    ेच
    0.06
     bent
    0.06
    aly
    0.06
     Unc
    0.06
    Act Density 0.014%

    No Known Activations