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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sicher
    -0.06
    HeaderValue
    -0.06
     Basil
    -0.06
     misunderstanding
    -0.06
     getService
    -0.06
     rubbish
    -0.06
    Ey
    -0.06
    asil
    -0.06
    MFLOAT
    -0.06
     dostup
    -0.06
    POSITIVE LOGITS
    Inverse
    0.07
    agli
    0.07
    (logger
    0.06
    280
    0.06
    ану
    0.06
     خواهند
    0.06
     đánh
    0.06
    ])))↵
    0.06
    29
    0.06
     имя
    0.06
    Act Density 0.043%

    No Known Activations