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

    Neuronpedia

    INDEX
    Explanations

    because whenever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Flu
    0.50
    /
    0.50
     Tut
    0.49
     Share
    0.49
     PV
    0.48
     Appl
    0.48
     Also
    0.48
     provides
    0.47
     auch
    0.46
     Pel
    0.46
    POSITIVE LOGITS
     терро
    0.46
     forêt
    0.46
    ীষ্ম
    0.45
     artık
    0.44
    ೀವ
    0.43
     이제
    0.43
    èce
    0.42
    PERSON
    0.42
    ̉i
    0.42
     terrorism
    0.41
    Act Density 0.003%

    No Known Activations