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

    Neuronpedia

    INDEX
    Explanations

    an error or unexpected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iber
    0.69
     Jol
    0.66
     miss
    0.65
     courses
    0.64
    miss
    0.63
    ืน
    0.62
     notched
    0.61
     Croix
    0.60
     clauses
    0.59
     JN
    0.59
    POSITIVE LOGITS
     जबकि
    0.79
     aan
    0.72
    ține
    0.69
     جبکہ
    0.69
     Watercolor
    0.69
     Schutz
    0.67
    Watercolor
    0.67
    凈
    0.66
     Eing
    0.66
     Schule
    0.66
    Act Density 0.080%

    No Known Activations