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

    Neuronpedia

    INDEX
    Explanations

    know anything or tell me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Oiseaux
    0.51
     than
    0.50
     underwhelming
    0.49
    ט
    0.49
    taking
    0.48
     Chestnut
    0.48
     бли
    0.47
     fundraiser
    0.47
     EIR
    0.47
     Анд
    0.47
    POSITIVE LOGITS
    as
    0.51
     қили
    0.46
     résult
    0.44
    NEGATIVE
    0.44
    怛
    0.44
     vagy
    0.43
    a
    0.42
     masch
    0.42
    pä
    0.42
    टर
    0.42
    Act Density 0.000%

    No Known Activations