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

    Neuronpedia

    INDEX
    Explanations

    risk assessment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orro
    -0.06
     impeccable
    -0.06
    З
    -0.06
     gained
    -0.06
    ecies
    -0.06
     Worth
    -0.06
     Soon
    -0.06
     другого
    -0.05
     thu
    -0.05
     věci
    -0.05
    POSITIVE LOGITS
    BindView
    0.07
     Prospect
    0.07
    aze
    0.07
    ilinx
    0.07
    ightly
    0.07
    >&
    0.07
    compet
    0.06
     inspector
    0.06
    _gui
    0.06
    гра
    0.06
    Act Density 0.025%

    No Known Activations