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

    Neuronpedia

    INDEX
    Explanations

    that + verb of action/state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻊ
    0.31
    ва
    0.31
    রাও
    0.31
    рав
    0.30
    m
    0.30
     aparel
    0.29
    0.29
    ரத்தில்
    0.29
     WLAN
    0.29
    রা
    0.28
    POSITIVE LOGITS
     a
    0.42
     години
    0.33
    acht
    0.32
    ón
    0.31
    ció
    0.31
    كا
    0.30
    iche
    0.30
    iguous
    0.29
     montaña
    0.29
    ín
    0.29
    Act Density 0.111%

    No Known Activations