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

    Neuronpedia

    INDEX
    Explanations

    potential, emerging, peak, involving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ش
    0.55
    ث
    0.48
    畱
    0.45
    7
    0.42
    Sciences
    0.42
    Specifically
    0.42
    Hours
    0.40
    0.40
    ام
    0.40
    ص
    0.40
    POSITIVE LOGITS
    ក្រុមហ៊ុន
    0.50
     белорус
    0.49
    signUp
    0.49
    𝚁
    0.48
    cccnc
    0.48
     popOperand
    0.48
     Беларусь
    0.47
     Gazprom
    0.47
     опас
    0.46
     бое
    0.46
    Act Density 0.000%

    No Known Activations