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

    Neuronpedia

    INDEX
    Explanations

    volumes and numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     editors
    -0.07
    camatan
    -0.07
     sued
    -0.07
    Emily
    -0.07
    .editor
    -0.06
    الم
    -0.06
    /csv
    -0.06
     qi
    -0.06
    扈
    -0.06
     للم
    -0.06
    POSITIVE LOGITS
    ߦ
    0.07
    통신
    0.07
     termination
    0.07
    堕
    0.07
    Different
    0.07
     nearing
    0.07
     fian
    0.06
    :get
    0.06
    _comp
    0.06
    peria
    0.06
    Act Density 0.034%

    No Known Activations