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

    Neuronpedia

    INDEX
    Explanations

    feelings and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isely
    0.38
     Ox
    0.35
    டியாக
    0.35
    ત્મક
    0.34
     فاصله
    0.34
     ox
    0.34
     confided
    0.33
    sus
    0.33
    ucht
    0.33
    &)
    0.33
    POSITIVE LOGITS
     doing
    0.49
    ശ്ശ
    0.46
     coalitions
    0.43
     testifying
    0.40
    ťa
    0.40
     stopp
    0.40
    लेश
    0.39
     谢
    0.39
     tetr
    0.39
     tard
    0.38
    Act Density 0.001%

    No Known Activations