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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WHO
    -0.07
     Jian
    -0.06
    واء
    -0.06
    ΟΤ
    -0.06
    범
    -0.06
     outrage
    -0.06
     Mu
    -0.06
     maxHeight
    -0.06
     quốc
    -0.06
    jee
    -0.06
    POSITIVE LOGITS
    =False
    0.07
    _='
    0.06
     addCriterion
    0.06
     sig
    0.06
    люча
    0.06
     fields
    0.06
    animated
    0.06
     сказ
    0.06
     برخورد
    0.06
    /St
    0.06
    Act Density 0.003%

    No Known Activations