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

    Neuronpedia

    INDEX
    Explanations

    grab quickly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     devoting
    0.39
    hacking
    0.38
     sugi
    0.38
     уют
    0.37
     meticul
    0.37
    жин
    0.37
    вної
    0.37
     wilfully
    0.37
     pregi
    0.37
    akti
    0.36
    POSITIVE LOGITS
     grab
    0.98
    grab
    0.82
     grabbing
    0.81
    Grab
    0.78
     quick
    0.77
     grabbed
    0.71
     Grab
    0.71
    grabbing
    0.71
    quickly
    0.69
     grabs
    0.69
    Act Density 0.016%

    No Known Activations