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

    Neuronpedia

    INDEX
    Explanations

    keywords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .d
    -0.07
     hatch
    -0.07
     рекоменду
    -0.06
    .load
    -0.06
    _backup
    -0.06
    attery
    -0.06
    renders
    -0.06
    ตะ
    -0.06
     underestimate
    -0.06
     söyl
    -0.06
    POSITIVE LOGITS
    -prof
    0.07
    áci
    0.06
     कई
    0.06
     menor
    0.06
     کار
    0.06
     شهری
    0.06
    ByKey
    0.06
     seeds
    0.06
     친구
    0.06
    objective
    0.06
    Act Density 0.003%

    No Known Activations