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

    Neuronpedia

    INDEX
    Explanations

    task instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ="
    0.71
     futurs
    0.67
     prospective
    0.65
     linseed
    0.64
     \
    0.63
     müşteri
    0.62
    _{-\
    0.61
    _{
    0.60
     popolo
    0.60
     fisi
    0.60
    POSITIVE LOGITS
    ซึ่ง
    0.59
    馊
    0.58
    acetic
    0.57
    abilistic
    0.56
    ist
    0.55
    नावश्यक
    0.55
    ப்பாக
    0.53
     sozinho
    0.53
    |,
    0.52
     interag
    0.52
    Act Density 0.001%

    No Known Activations