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

    Neuronpedia

    INDEX
    Explanations

    junit and json in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rush
    0.38
    كمال
    0.38
    agement
    0.36
    autogui
    0.36
    имуще
    0.35
    ርግ
    0.35
    rush
    0.35
     compat
    0.34
    énagement
    0.34
    ̀
    0.34
    POSITIVE LOGITS
    paypal
    0.39
    ቭ
    0.39
    🏨
    0.38
     গল
    0.38
     Protección
    0.38
     acheter
    0.37
     चित्रा
    0.37
     ......
    0.37
    ➘
    0.36
    ovol
    0.36
    Act Density 0.000%

    No Known Activations