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

    Neuronpedia

    INDEX
    Explanations

    filter by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iptic
    0.43
    acuation
    0.43
    表的
    0.43
    都
    0.42
    ைகோ
    0.41
    ontium
    0.41
     الدنيا
    0.41
    encountered
    0.39
     nailing
    0.39
    сле
    0.39
    POSITIVE LOGITS
    rives
    0.43
     Nachhalt
    0.40
    fice
    0.38
    oacute
    0.37
     ví
    0.37
    heiz
    0.37
     felt
    0.36
    ]。
    0.36
     облада
    0.36
    Pul
    0.36
    Act Density 0.001%

    No Known Activations