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

    Neuronpedia

    INDEX
    Explanations

    grabbed or caught

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نرخ
    0.40
     Compd
    0.40
     ერთი
    0.39
    ISPW
    0.38
     丶
    0.38
     Eintrag
    0.37
     leche
    0.37
    zony
    0.37
    氇
    0.36
     Ozone
    0.36
    POSITIVE LOGITS
     grabbed
    0.71
    抓
    0.70
     grab
    0.67
     caught
    0.66
    grab
    0.66
     grabbing
    0.65
    Grab
    0.63
    抓住
    0.63
    grabbing
    0.63
     catching
    0.63
    Act Density 0.000%

    No Known Activations