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

    Neuronpedia

    INDEX
    Explanations

    be treated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.95
    f
    0.73
    in
    0.70
    u
    0.67
    ar
    0.64
    an
    0.63
    ation
    0.58
    it
    0.58
    al
    0.58
    at
    0.57
    POSITIVE LOGITS
     personnes
    0.59
     bacterias
    0.55
     microorganism
    0.55
     harnessed
    0.54
    種の
    0.54
     edilir
    0.54
     disciplinas
    0.52
    صاص
    0.50
     construed
    0.50
    лькі
    0.50
    Act Density 0.000%

    No Known Activations