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

    Neuronpedia

    INDEX
    Explanations

    Javascript code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Phys
    -0.08
     physically
    -0.08
     restring
    -0.08
     ACH
    -0.08
     avant
    -0.08
     ér
    -0.07
     Indo
    -0.07
     induct
    -0.07
     scant
    -0.07
     гр
    -0.07
    POSITIVE LOGITS
    conditional
    0.10
     оператор
    0.10
    Conditional
    0.10
     Conditional
    0.10
     conditional
    0.09
    Operator
    0.09
    _operator
    0.09
    保险
    0.09
     operador
    0.09
    括
    0.09
    Act Density 0.005%

    No Known Activations