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

    Neuronpedia

    INDEX
    Explanations

    user

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nas
    -0.07
     wind
    -0.07
     Treat
    -0.07
    stk
    -0.07
    fern
    -0.06
    Las
    -0.06
    ائر
    -0.06
     Prom
    -0.06
    払
    -0.06
    owski
    -0.06
    POSITIVE LOGITS
    dden
    0.07
    necessary
    0.06
    :no
    0.06
     bcm
    0.06
     injunction
    0.06
     /*
↵
    0.06
    .onView
    0.06
     bosses
    0.06
    ива
    0.06
    ระยะ
    0.06
    Act Density 0.021%

    No Known Activations