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

    Neuronpedia

    INDEX
    Explanations

    informative comprehensive way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bry
    0.43
    ।--
    0.39
    lov
    0.38
    欤
    0.38
     Combien
    0.38
    ươi
    0.37
    ？」
    0.36
    颛
    0.36
    逈
    0.36
    丶
    0.36
    POSITIVE LOGITS
    투자
    0.35
    лиз
    0.35
     داعش
    0.34
     cohesion
    0.34
     despite
    0.34
    ০০০
    0.33
    дена
    0.33
     ठाकरे
    0.32
     chủ
    0.32
     Lockdown
    0.32
    Act Density 0.079%

    No Known Activations