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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    poses
    -0.08
     exploit
    -0.08
     ephemeral
    -0.07
    verse
    -0.07
     exploited
    -0.07
     verse
    -0.07
     explotación
    -0.07
     exploitation
    -0.07
    Compared
    -0.07
     ubr
    -0.07
    POSITIVE LOGITS
     সরকারের
    0.08
    oban
    0.08
    /right
    0.08
     Fortsch
    0.08
     Zahlungsm
    0.08
     لارې
    0.08
    -wide
    0.07
     সংশ
    0.07
    וין
    0.07
    右
    0.07
    Act Density 0.003%

    No Known Activations