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

    Neuronpedia

    INDEX
    Explanations

    other languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Status
    -0.07
    (id
    -0.06
    linear
    -0.06
     interested
    -0.06
     ret
    -0.06
     Ð
    -0.06
     Kentucky
    -0.06
     Ethics
    -0.06
    (ret
    -0.06
    Ð
    -0.06
    POSITIVE LOGITS
    ание
    0.07
    -founded
    0.07
    Inicio
    0.07
    .rar
    0.07
    �
    0.06
     RecognitionException
    0.06
     다시
    0.06
     manner
    0.06
     unmistak
    0.06
     रक
    0.06
    Act Density 0.050%

    No Known Activations