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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sanctuary
    -0.07
     Quebec
    -0.06
     фінанс
    -0.06
     sala
    -0.06
     enticing
    -0.06
    OWL
    -0.06
     getaway
    -0.06
    CLR
    -0.06
     Indonesian
    -0.06
    Hel
    -0.06
    POSITIVE LOGITS
     Forty
    0.07
     [`
    0.06
    formulario
    0.06
     dummy
    0.06
     ########################
    0.06
     Gerald
    0.06
    Declaration
    0.06
     django
    0.06
    影響
    0.06
     formulas
    0.06
    Act Density 0.009%

    No Known Activations