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

    Neuronpedia

    INDEX
    Explanations

    possessions, experiences, states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    0.47
    ك
    0.46
    ০০
    0.36
    for
    0.36
     அவள்
    0.32
     ，
    0.32
    다면
    0.31
    0
    0.31
    т
    0.31
    나
    0.31
    POSITIVE LOGITS
     been
    0.66
    ע
    0.52
    been
    0.49
     BEEN
    0.43
     Been
    0.41
     sido
    0.40
     had
    0.36
    Been
    0.36
    明显的
    0.35
    ס
    0.34
    Act Density 0.265%

    No Known Activations