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

    Neuronpedia

    INDEX
    Explanations

    tf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     booths
    -0.06
     dispose
    -0.06
    この
    -0.06
    सर
    -0.06
    _de
    -0.06
    -Д
    -0.06
     Competition
    -0.06
    Forgot
    -0.06
     vào
    -0.06
    욕
    -0.06
    POSITIVE LOGITS
     theano
    0.07
    xfff
    0.07
    nums
    0.07
     NP
    0.06
    _'
    0.06
    .ItemStack
    0.06
    _]
    0.06
     часа
    0.06
    951
    0.06
     Detected
    0.06
    Act Density 0.003%

    No Known Activations