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

    Neuronpedia

    INDEX
    Explanations

    ranging from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    és
    0.57
    pe
    0.54
    ime
    0.54
    ank
    0.52
    л
    0.52
    ip
    0.51
    us
    0.51
    ón
    0.51
    ola
    0.50
    ően
    0.48
    POSITIVE LOGITS
     electroph
    0.58
     Interpreter
    0.58
     interpre
    0.53
     interpreter
    0.52
     interpreters
    0.52
     experi
    0.51
    a
    0.51
    s
    0.51
     erfol
    0.50
    申し
    0.50
    Act Density 0.000%

    No Known Activations