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

    Neuronpedia

    INDEX
    Explanations

    arterial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enderror
    -0.07
    campo
    -0.07
    .gwt
    -0.06
    estival
    -0.06
     kariy
    -0.06
    _brand
    -0.06
     використ
    -0.06
     fame
    -0.06
    formerly
    -0.06
    есп
    -0.06
    POSITIVE LOGITS
     closure
    0.06
     arrangements
    0.06
     (){↵
    0.06
     short
    0.06
     restriction
    0.06
    UDA
    0.06
    Length
    0.06
    _SPACE
    0.06
     {"
    0.06
     secret
    0.06
    Act Density 0.002%

    No Known Activations