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

    Neuronpedia

    INDEX
    Explanations

    cyrillic script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eqn
    0.66
    thisStudent
    0.66
     expts
    0.66
     supernat
    0.59
     optar
    0.58
    setlength
    0.57
    цију
    0.57
    ښت
    0.56
     psychosocial
    0.56
    ædia
    0.56
    POSITIVE LOGITS
     С
    1.42
     с
    1.29
     Т
    1.16
     М
    1.16
    С
    1.16
     А
    1.15
     а
    1.13
     К
    1.11
     №
    1.09
     Р
    1.08
    Act Density 0.018%

    No Known Activations