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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (extra
    -0.06
    	html
    -0.06
     العق
    -0.06
     intercourse
    -0.06
     Sunday
    -0.06
    _PREVIEW
    -0.06
    /Typography
    -0.06
     ceased
    -0.06
     plist
    -0.06
    pars
    -0.06
    POSITIVE LOGITS
    NotNull
    0.07
     dijo
    0.06
    луг
    0.06
     ga
    0.06
     LTE
    0.06
     deserves
    0.06
     marrow
    0.06
    Affected
    0.06
     Golf
    0.06
    _ROLE
    0.06
    Act Density 0.079%

    No Known Activations