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

    Neuronpedia

    INDEX
    Explanations

    fun exercise, scrum, fishing, things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Χ
    1.12
     साहस
    1.00
    ওর
    0.97
     bellezza
    0.97
    en
    0.96
    тың
    0.96
    Lovely
    0.90
     kuat
    0.88
    Beauty
    0.87
    優れた
    0.87
    POSITIVE LOGITS
    nels
    1.86
    erals
    1.67
    nier
    1.65
    ktional
    1.60
    nies
    1.56
    icular
    1.47
    tional
    1.47
    niest
    1.40
    nel
    1.35
    nym
    1.34
    Act Density 0.031%

    No Known Activations