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

    Neuronpedia

    INDEX
    Explanations

    finding or where to find

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мою
    0.72
    első
    0.70
     നടത്തിയ
    0.69
    ことを
    0.68
    मेरी
    0.66
     मेरी
    0.66
    のか
    0.66
     Roskov
    0.65
     minha
    0.64
    visited
    0.63
    POSITIVE LOGITS
     found
    1.58
     find
    1.39
     finding
    1.29
    found
    1.29
     Found
    1.26
     finds
    1.25
     Find
    1.21
    Found
    1.19
     encontrarás
    1.18
    Find
    1.18
    Act Density 0.512%

    No Known Activations