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

    Neuronpedia

    INDEX
    Explanations

    bank

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Write
    -0.07
    ROUP
    -0.07
    けて
    -0.07
    أنو
    -0.07
    Into
    -0.07
    資金
    -0.07
    сли
    -0.07
     encode
    -0.06
    arching
    -0.06
     Müller
    -0.06
    POSITIVE LOGITS
     identities
    0.06
    _intersection
    0.06
    쁜
    0.06
     screenplay
    0.06
     тек
    0.06
    峧
    0.06
     Highlands
    0.06
    👮
    0.06
    くだ
    0.06
    'I
    0.06
    Act Density 0.002%

    No Known Activations