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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     illeg
    -0.07
    )L
    -0.07
    -reaching
    -0.07
     roll
    -0.07
    'L
    -0.07
     aras
    -0.07
    ,l
    -0.07
     hil
    -0.06
    *L
    -0.06
    omedical
    -0.06
    POSITIVE LOGITS
     stressed
    0.07
    _status
    0.07
    ้าส
    0.07
    sad
    0.07
    SMS
    0.07
    _so
    0.07
    .SO
    0.07
    		  ↵
    0.07
    ToProps
    0.07
    SID
    0.07
    Act Density 2.550%

    No Known Activations