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

    Neuronpedia

    INDEX
    Explanations

    same macroscopic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.43
    ડી
    0.42
     тока
    0.41
    cutoff
    0.41
    cott
    0.40
    awareness
    0.40
    Payload
    0.39
    ksi
    0.39
    _%
    0.39
    otoxicity
    0.39
    POSITIVE LOGITS
     incol
    0.52
    મને
    0.46
    ിത്ര
    0.46
     Lorsqu
    0.46
     quando
    0.46
     vous
    0.46
     നിങ്ങൾ
    0.46
     insegn
    0.44
     Ihnen
    0.41
     aprove
    0.41
    Act Density 0.001%

    No Known Activations