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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iki
    -0.07
    estro
    -0.07
     Hassan
    -0.07
     sulla
    -0.07
    들의
    -0.07
     alt
    -0.07
     samsung
    -0.06
    ragment
    -0.06
    แกรม
    -0.06
     headaches
    -0.06
    POSITIVE LOGITS
    .cwd
    0.06
     Todd
    0.06
     climate
    0.06
    .variant
    0.05
     conviction
    0.05
     iteration
    0.05
    在线
    0.05
     rounds
    0.05
    vä
    0.05
    _SCORE
    0.05
    Act Density 0.002%

    No Known Activations