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

    Neuronpedia

    INDEX
    Explanations

    score

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hx
    -0.07
    حق
    -0.07
     seals
    -0.06
    Unsupported
    -0.06
     }),↵
    -0.06
     sealing
    -0.06
    ssh
    -0.06
    _LINEAR
    -0.06
    ไร
    -0.06
     steril
    -0.06
    POSITIVE LOGITS
    folder
    0.08
     Significant
    0.06
    (itemView
    0.06
     将
    0.06
     poets
    0.06
     SCORE
    0.06
    <?=$
    0.06
     और
    0.06
     imprison
    0.06
     Beacon
    0.06
    Act Density 0.010%

    No Known Activations