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

    Neuronpedia

    INDEX
    Explanations

    Math/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    虷
    -0.08
    (A
    -0.07
    dt
    -0.07
     cape
    -0.07
    เสา
    -0.06
    .utils
    -0.06
    _entity
    -0.06
     Absolute
    -0.06
     skill
    -0.06
    	n
    -0.06
    POSITIVE LOGITS
    Refer
    0.08
     Beg
    0.08
     moet
    0.07
     Drive
    0.07
     paired
    0.07
    错
    0.07
    _REFERER
    0.07
    תפר
    0.07
     Jord
    0.07
     Gujar
    0.06
    Act Density 0.011%

    No Known Activations