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

    Neuronpedia

    INDEX
    Explanations

    letter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kvinder
    -0.07
     camouflage
    -0.07
    ToListAsync
    -0.07
    _td
    -0.07
     xa
    -0.07
     têm
    -0.06
     faction
    -0.06
    Comfort
    -0.06
    PHP
    -0.06
    ;s
    -0.06
    POSITIVE LOGITS
     letter
    0.09
     Letter
    0.08
     let
    0.07
    _LOOP
    0.07
     letters
    0.07
    /model
    0.06
    _front
    0.06
    gmail
    0.06
     günü
    0.06
    cion
    0.06
    Act Density 0.017%

    No Known Activations