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

    Neuronpedia

    INDEX
    Explanations

    possessive determiners followed by body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rôle
    0.43
     Role
    0.41
    }}}^{
    0.40
    標
    0.40
    ේ
    0.39
    标
    0.39
    *}\
    0.38
    }->
    0.38
     úlo
    0.38
    বস
    0.37
    POSITIVE LOGITS
     eyes
    0.53
     கூடிய
    0.53
     hands
    0.48
     fists
    0.47
     Eyes
    0.46
     backs
    0.45
    hands
    0.45
    backs
    0.44
    Hands
    0.44
    全て
    0.44
    Act Density 0.012%

    No Known Activations