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

    Neuronpedia

    INDEX
    Explanations

    enclosure punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sterilization
    0.47
     confidentiality
    0.46
     sectores
    0.46
    (':
    0.45
    ্ডার
    0.44
     pathogens
    0.43
     applicability
    0.43
    9
    0.43
    খি
    0.43
    arity
    0.43
    POSITIVE LOGITS
     Gage
    0.49
     lesión
    0.47
     colère
    0.46
     limón
    0.46
     Brut
    0.45
    Correspond
    0.45
     convexe
    0.44
    欬
    0.44
     இறைவன்
    0.43
     Благодаря
    0.43
    Act Density 0.009%

    No Known Activations