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

    Neuronpedia

    INDEX
    Explanations

    identity or existence statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     нашего
    0.52
     naszego
    0.50
     naszej
    0.48
     ہمارے
    0.47
     нашей
    0.44
     нашем
    0.43
     estando
    0.43
     nostro
    0.42
     unserer
    0.42
     باشه
    0.42
    POSITIVE LOGITS
     inextricably
    0.63
     sculpted
    0.55
     molded
    0.54
     unapolog
    0.51
     composed
    0.50
     proof
    0.46
     the
    0.46
     inextric
    0.46
     powerfully
    0.46
     transformative
    0.45
    Act Density 0.015%

    No Known Activations