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

    Neuronpedia

    INDEX
    Explanations

    the contraction "let's"

    oai_token-act-pair · gemini-2.0-flash

    verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    autoconfigure
    -0.71
     محفوظة
    -0.68
     Signalez
    -0.66
     Let
    -0.63
    Let
    -0.62
    lets
    -0.60
    posedge
    -0.59
     Holtz
    -0.58
     lets
    -0.58
     letting
    -0.57
    POSITIVE LOGITS
     autorytatywna
    0.68
     Roskov
    0.59
     play
    0.59
    tvguidetime
    0.59
    ofollow
    0.57
    Hochspringen
    0.57
     disarm
    0.56
    rungsseite
    0.56
     combine
    0.54
     rinse
    0.53
    Act Density 0.854%

    No Known Activations