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

    Neuronpedia

    INDEX
    Explanations

    conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    get
    -0.06
    Professor
    -0.06
    لوب
    -0.06
    18
    -0.06
     cursed
    -0.06
     asserted
    -0.06
    upload
    -0.06
    _attr
    -0.06
    rack
    -0.06
    Choose
    -0.06
    POSITIVE LOGITS
     kä
    0.07
     nhu
    0.06
    aises
    0.06
     Leg
    0.06
     Except
    0.06
    .Ap
    0.06
    ,false
    0.06
     OMIT
    0.06
     первого
    0.06
     mov
    0.06
    Act Density 0.037%

    No Known Activations