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

    Neuronpedia

    INDEX
    Explanations

    speak about everyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Чу
    0.52
    ذیر
    0.51
    法則
    0.50
    ྥ
    0.49
    حمد
    0.47
     சிறு
    0.46
    анали
    0.46
     adduct
    0.45
    الج
    0.45
    аб
    0.44
    POSITIVE LOGITS
    ",
    0.57
    "
    0.55
    ".
    0.53
    umen
    0.50
     Landing
    0.48
    ]
    0.48
    ümü
    0.47
    on
    0.47
    .",
    0.46
    ."
    0.45
    Act Density 0.000%

    No Known Activations