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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _square
    -0.06
     amt
    -0.06
     thiết
    -0.06
     withd
    -0.06
    �
    -0.06
     organ
    -0.06
     }])↵
    -0.06
    arten
    -0.06
     Ven
    -0.06
     Blink
    -0.06
    POSITIVE LOGITS
    -aware
    0.06
     кот
    0.06
    zers
    0.06
    ivating
    0.06
    uckles
    0.06
    _tipo
    0.06
    ensagem
    0.06
    ategorias
    0.06
     enumerated
    0.06
     madre
    0.06
    Act Density 0.001%

    No Known Activations