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

    Neuronpedia

    INDEX
    Explanations

    terms and license usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     retardation
    0.46
     zeroes
    0.43
     লা
    0.41
    IONI
    0.41
     massima
    0.40
     LOCCTR
    0.39
     glTexCoord
    0.38
     exportation
    0.38
     considerazione
    0.38
     "=
    0.37
    POSITIVE LOGITS
    ner
    0.46
    ourcing
    0.45
    ary
    0.45
    ija
    0.44
     Team
    0.44
    od
    0.43
    ::{
    0.43
    ’
    0.43
     Bit
    0.42
    ung
    0.42
    Act Density 0.005%

    No Known Activations