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

    Neuronpedia

    INDEX
    Explanations

    technical terms and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     worldwide
    0.43
    ertations
    0.42
    Israeli
    0.41
    UserDetails
    0.39
     unaltered
    0.39
     Israeli
    0.38
     Qxd
    0.38
     pioneering
    0.38
     pioneer
    0.37
     departmental
    0.37
    POSITIVE LOGITS
    emo
    0.39
    petal
    0.38
    pv
    0.38
    otek
    0.38
    ören
    0.37
    edil
    0.37
    ستی
    0.37
    ektiv
    0.37
    ha
    0.36
    élène
    0.36
    Act Density 0.001%

    No Known Activations