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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trey
    -0.07
    icker
    -0.06
     `;↵
    -0.06
    _qos
    -0.06
    _listing
    -0.06
    носят
    -0.06
     Zucker
    -0.06
    classic
    -0.06
     daemon
    -0.06
    $client
    -0.06
    POSITIVE LOGITS
     upset
    0.07
     mata
    0.07
     diminishing
    0.07
     VE
    0.07
     balanced
    0.07
     tidak
    0.06
    ightly
    0.06
     efficiently
    0.06
     regeneration
    0.06
     اینچ
    0.06
    Act Density 0.003%

    No Known Activations