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

    Neuronpedia

    INDEX
    Explanations

    positive sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сос
    -0.07
     Eventually
    -0.07
    уста
    -0.07
     treff
    -0.07
    robat
    -0.07
    (gca
    -0.07
    efs
    -0.06
     Україна
    -0.06
    bos
    -0.06
    yps
    -0.06
    POSITIVE LOGITS
    .Keyword
    0.06
     Knoxville
    0.06
     press
    0.06
     walkthrough
    0.06
    _HOUR
    0.06
     digest
    0.06
    heading
    0.06
     passphrase
    0.06
     исполн
    0.05
    ennial
    0.05
    Act Density 0.051%

    No Known Activations