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

    Neuronpedia

    INDEX
    Explanations

    Italian, Korean, French

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     બી
    0.50
     ಗಳ
    0.46
     போது
    0.46
     அவரின்
    0.46
    <unused635>
    0.46
     कित
    0.45
    ಟ್ರ
    0.45
    벅
    0.45
     glandes
    0.44
    לי
    0.44
    POSITIVE LOGITS
     Italian
    0.50
     new
    0.49
     grants
    0.49
    -
    0.49
     shirts
    0.47
     Vue
    0.46
     nye
    0.46
     novo
    0.45
     nouvelle
    0.45
    「
    0.45
    Act Density 0.005%

    No Known Activations