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

    Neuronpedia

    INDEX
    Explanations

    Trevor Project .org

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نسب
    0.63
    дис
    0.61
     sup
    0.61
    တင်
    0.60
    ፊት
    0.59
    colgroup
    0.59
     chains
    0.59
     composites
    0.58
    せ
    0.57
     composite
    0.57
    POSITIVE LOGITS
    腎
    0.74
    Ę
    0.68
    ked
    0.67
     officia
    0.67
    ਿੰ
    0.65
     KELL
    0.65
     merge
    0.65
     îi
    0.64
    agher
    0.64
     merges
    0.64
    Act Density 0.238%

    No Known Activations