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

    Neuronpedia

    INDEX
    Explanations

    both a and b

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     terminology
    0.49
     ediciones
    0.49
     bleak
    0.48
    اتها
    0.48
     преподава
    0.47
     potter
    0.46
     Machinery
    0.46
     glimmer
    0.45
     hissed
    0.45
     dissonance
    0.45
    POSITIVE LOGITS
    cyj
    0.50
    date
    0.47
    U
    0.46
    forward
    0.45
     неф
    0.44
    fasta
    0.44
    dan
    0.43
    listBox
    0.43
    nonumber
    0.43
    P
    0.42
    Act Density 0.001%

    No Known Activations