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

    Neuronpedia

    INDEX
    Explanations

    alternatives and exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ar
    0.38
     encoding
    0.38
     encoded
    0.35
     um
    0.35
    泽
    0.35
    abilités
    0.34
     diameter
    0.34
     ar
    0.34
     dependency
    0.34
     IntelliJ
    0.34
    POSITIVE LOGITS
     применение
    0.44
    getMetering
    0.41
    akkam
    0.40
    hattim
    0.39
    样品
    0.38
    anteen
    0.38
     apice
    0.37
    ólito
    0.37
    aneers
    0.36
     Бүгенге
    0.36
    Act Density 0.000%

    No Known Activations