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

    Neuronpedia

    INDEX
    Explanations

    Actions and statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buff
    -0.07
     Foods
    -0.07
     material
    -0.07
     philosophy
    -0.06
     alarm
    -0.06
     ----------------------------------------------------------------
    -0.06
     оз
    -0.06
     sheets
    -0.06
    .ReadOnly
    -0.06
    044
    -0.06
    POSITIVE LOGITS
    ternet
    0.07
     Trần
    0.07
    ังก
    0.06
    ريقة
    0.06
     style
    0.06
    ==(
    0.06
     случай
    0.06
     anderen
    0.06
    Premium
    0.06
    ربه
    0.06
    Act Density 0.074%

    No Known Activations