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

    Neuronpedia

    INDEX
    Explanations

    programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    over
    0.65
    cutter
    0.58
     こちら
    0.55
    bunny
    0.55
     పాటు
    0.54
    慓
    0.52
    cut
    0.52
    cott
    0.52
    leur
    0.51
     μπο
    0.51
    POSITIVE LOGITS
     activar
    0.65
    া
    0.63
    ه
    0.59
    ב
    0.59
     enfrentar
    0.58
    ET
    0.57
    0.56
     eTo
    0.55
    ক
    0.55
    จะ
    0.54
    Act Density 0.001%

    No Known Activations