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

    Neuronpedia

    INDEX
    Explanations

    movie Get Out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonzero
    0.25
     nonnegative
    0.24
    ারিত
    0.23
     ifelse
    0.22
     bodied
    0.22
     '.$
    0.21
     utilice
    0.21
     probabilistic
    0.21
     behov
    0.21
     nilpotent
    0.21
    POSITIVE LOGITS
     Ба
    0.22
    Giant
    0.21
     sprawling
    0.20
    M
    0.20
    P
    0.19
    Dar
    0.19
    Lis
    0.19
    당
    0.19
    River
    0.19
     огром
    0.19
    Act Density 0.127%

    No Known Activations