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

    Neuronpedia

    INDEX
    Explanations

    Scored goal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruined
    -0.07
    <=(
    -0.07
    θούν
    -0.06
    Viol
    -0.06
    viol
    -0.06
     Oh
    -0.06
    ?>
    -0.06
     bombing
    -0.06
    IMAL
    -0.06
    ))]
    -0.06
    POSITIVE LOGITS
     python
    0.06
    CHED
    0.06
     eks
    0.06
     color
    0.06
    WC
    0.06
    dech
    0.06
     піс
    0.06
    intel
    0.06
     авт
    0.06
    edes
    0.06
    Act Density 0.012%

    No Known Activations