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

    Neuronpedia

    INDEX
    Explanations

    risk assessment, tolerance, reward

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ים
    2.98
    cology
    2.87
    та
    2.81
    ckpt
    2.59
    sir
    2.57
    sion
    2.49
    𝙜
    2.46
    ت
    2.45
    smoking
    2.43
    isinde
    2.41
    POSITIVE LOGITS
    л
    2.73
    𝗻
    2.69
     averse
    2.60
    도
    2.59
    っと
    2.54
    ણી
    2.45
    ه
    2.42
    אים
    2.42
    𝗮
    2.39
    𝗲
    2.38
    Act Density 0.061%

    No Known Activations