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

    Neuronpedia

    INDEX
    Explanations

    highlights themes and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    कोण
    0.42
     Apakah
    0.42
     Which
    0.40
     कोणत्या
    0.36
     Basically
    0.35
     якого
    0.35
     quoi
    0.34
     whos
    0.34
    儼
    0.34
    Which
    0.34
    POSITIVE LOGITS
     how
    0.53
     themes
    0.49
     why
    0.49
     parallels
    0.46
     faptul
    0.46
    how
    0.45
    why
    0.45
     bagaimana
    0.44
     notions
    0.44
    themes
    0.43
    Act Density 0.092%

    No Known Activations