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

    Neuronpedia

    INDEX
    Explanations

    ver

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أخ
    -0.07
     humour
    -0.07
     Estados
    -0.07
    	Path
    -0.06
    _qp
    -0.06
     Bas
    -0.06
     Pant
    -0.06
     Dash
    -0.06
     Plat
    -0.06
     możli
    -0.06
    POSITIVE LOGITS
     attributes
    0.06
     sessiz
    0.06
    _rules
    0.06
     تصویر
    0.06
    _InitStruct
    0.06
     yaptık
    0.06
     stew
    0.06
     thaw
    0.06
    0.06
    聞
    0.06
    Act Density 0.205%

    No Known Activations