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

    Neuronpedia

    INDEX
    Explanations

    the word "just" in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    just followed by past tense verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perros
    -0.34
    hombres
    -0.32
    PYX
    -0.31
     hombres
    -0.29
     humaine
    -0.28
     programme
    -0.28
     doch
    -0.28
    platten
    -0.26
    endiendo
    -0.26
     realistas
    -0.26
    POSITIVE LOGITS
     للتو
    0.81
    httphttps
    0.74
    recently
    0.73
     vừa
    0.72
    rungsseite
    0.71
     recently
    0.71
     appena
    0.71
    IntoConstraints
    0.68
     հղումներ
    0.65
     <<<<<<<<<<<<<<
    0.63
    Act Density 0.019%

    No Known Activations