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

    Neuronpedia

    INDEX
    Explanations

    get started, get yours, get a quote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (“
    0.53
    ρέπει
    0.48
     gewährleisten
    0.46
     entstehen
    0.45
    parvec
    0.45
     Betracht
    0.45
    ك
    0.45
    ಂಬ
    0.45
    LaunchScheme
    0.44
     деятельность
    0.44
    POSITIVE LOGITS
     rid
    0.79
     on
    0.63
     get
    0.51
     GET
    0.51
    z
    0.51
     '/
    0.50
     Rid
    0.50
     लि
    0.47
    म
    0.47
     [
    0.46
    Act Density 0.036%

    No Known Activations