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

    Neuronpedia

    INDEX
    Explanations

    color swatch and board

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pecan
    0.58
     favorit
    0.55
     yolk
    0.54
     participación
    0.52
     linseed
    0.51
    ຢູ່ໃນ
    0.50
     zipper
    0.50
     wax
    0.49
     nostalgia
    0.49
     パン
    0.49
    POSITIVE LOGITS
    అ
    0.46
    ĝ
    0.45
    riques
    0.44
    abilité
    0.43
    It
    0.43
    枟
    0.43
    ấ
    0.41
    說
    0.41
    baarheid
    0.41
    淸
    0.41
    Act Density 0.000%

    No Known Activations