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

    Neuronpedia

    INDEX
    Explanations

    No

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cottage
    -0.06
     cheating
    -0.06
    addy
    -0.06
    {|
    -0.06
     bast
    -0.06
    udd
    -0.06
    	ax
    -0.06
    cat
    -0.06
    acus
    -0.06
     Seas
    -0.06
    POSITIVE LOGITS
    Tensor
    0.07
     getLast
    0.07
     اجازه
    0.07
    开
    0.07
     उसक
    0.06
     Astro
    0.06
    _NE
    0.06
    _time
    0.06
    _goto
    0.06
    開
    0.06
    Act Density 0.005%

    No Known Activations