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

    Neuronpedia

    INDEX
    Explanations

    electrical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Prem
    -0.08
    jącym
    -0.07
     Medal
    -0.07
    ič
    -0.07
     Goodman
    -0.07
     Heads
    -0.07
     glasses
    -0.07
     Rolls
    -0.06
     stos
    -0.06
     الثالث
    -0.06
    POSITIVE LOGITS
    test
    0.07
    /request
    0.07
     seldom
    0.07
    .You
    0.07
     tent
    0.07
    🏬
    0.07
    数字化
    0.07
    𫔎
    0.07
     StringBuffer
    0.06
    outing
    0.06
    Act Density 0.010%

    No Known Activations