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

    Neuronpedia

    INDEX
    Explanations

    discovery and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    စိတ်အပိုင်း
    1.68
    $}
    1.62
    تان
    1.60
    서
    1.51
    Forge
    1.49
     refrained
    1.48
    gies
    1.45
    Encoder
    1.43
     οποία
    1.42
    arker
    1.41
    POSITIVE LOGITS
    𝗦
    1.88
    𝗣
    1.67
    ྛ
    1.62
    áneo
    1.61
    ৪
    1.59
     हुए
    1.59
     hordes
    1.59
    ый
    1.59
    গির
    1.58
    𝗺
    1.52
    Act Density 0.000%

    No Known Activations