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

    Neuronpedia

    INDEX
    Explanations

    ");"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ps
    -0.07
     hawk
    -0.06
    cial
    -0.06
    _g
    -0.06
     gallon
    -0.06
     Catholic
    -0.06
    อม
    -0.06
     الجام
    -0.06
     clich
    -0.06
     patrols
    -0.06
    POSITIVE LOGITS
     شود
    0.07
    .Take
    0.07
    relationship
    0.06
     تصمیم
    0.06
    FOR
    0.06
    śli
    0.06
     prostě
    0.06
     correction
    0.06
     inspir
    0.06
     محصولات
    0.06
    Act Density 0.016%

    No Known Activations