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

    Neuronpedia

    INDEX
    Explanations

    code and software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     адміністра
    -0.07
     dehydration
    -0.07
     名無し
    -0.07
     만나
    -0.07
    INTR
    -0.06
     herbal
    -0.06
     Allowed
    -0.06
     ['
    -0.06
     Bol
    -0.06
    ší
    -0.06
    POSITIVE LOGITS
    _Items
    0.06
     Yardım
    0.06
    _playlist
    0.06
    dělen
    0.06
    =========↵
    0.06
    ορειο
    0.06
    /cpp
    0.05
     estoy
    0.05
    latable
    0.05
    uft
    0.05
    Act Density 0.071%

    No Known Activations