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

    Neuronpedia

    INDEX
    Explanations

    Arithmetic calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тики
    -0.08
     cả
    -0.08
    mentor
    -0.08
     sapp
    -0.08
    Comm
    -0.07
     пить
    -0.07
    Crusher
    -0.07
     că
    -0.07
     troublesome
    -0.07
     Quinta
    -0.07
    POSITIVE LOGITS
     શુભ
    0.08
     countertops
    0.07
     policiais
    0.07
     doğ
    0.07
    .Payload
    0.07
     પોસ્ટ
    0.07
     ભૂ
    0.07
     backstage
    0.07
     અસ
    0.07
     પરિવ
    0.07
    Act Density 0.067%

    No Known Activations