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

    Neuronpedia

    INDEX
    Explanations

    come in or closer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,]$
    0.41
    स्तु
    0.40
     исходя
    0.39
    fassung
    0.38
    gın
    0.37
    gren
    0.37
     arriving
    0.36
    kowicz
    0.36
    zuf
    0.36
     isomeric
    0.36
    POSITIVE LOGITS
     visit
    0.58
     celebrate
    0.57
    Visit
    0.54
    Come
    0.53
     see
    0.50
     join
    0.50
     Closer
    0.49
     nearer
    0.48
     discuss
    0.48
     closer
    0.47
    Act Density 0.003%

    No Known Activations