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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (other
    -0.07
    ('*',
    -0.07
     HTTP
    -0.07
    degree
    -0.07
    .leadingAnchor
    -0.07
     dernière
    -0.06
     makeshift
    -0.06
    ordered
    -0.06
     limited
    -0.06
     Forecast
    -0.06
    POSITIVE LOGITS
     پي
    0.06
     articulated
    0.06
     felse
    0.06
    	TRACE
    0.06
     tweaks
    0.06
    Unused
    0.06
    straction
    0.06
     neutrality
    0.06
     *)
    0.06
     bilg
    0.06
    Act Density 0.000%

    No Known Activations