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

    Neuronpedia

    INDEX
    Explanations

    an answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ächer
    0.43
    vár
    0.41
     asociado
    0.41
     přip
    0.40
    remia
    0.40
    ordination
    0.40
    გ
    0.40
    Mediterranean
    0.39
    Associate
    0.39
    ੋਰ
    0.39
    POSITIVE LOGITS
     droid
    0.42
    深圳
    0.42
    㯎
    0.42
     및
    0.42
     Requirement
    0.41
     طریقے
    0.40
     chattel
    0.40
    的做法
    0.40
     tenue
    0.40
    CapsLock
    0.40
    Act Density 0.008%

    No Known Activations