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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ז
    0.41
    거나
    0.41
    ια
    0.38
    לא
    0.38
     ወይም
    0.38
     ή
    0.36
     எனப்படும்
    0.36
     ἢ
    0.35
    隹
    0.35
     או
    0.35
    POSITIVE LOGITS
     Emirates
    0.37
     %><%=
    0.36
     endgame
    0.35
     Leopard
    0.35
     Greenway
    0.35
     mijn
    0.34
     Philos
    0.34
     bych
    0.34
     peduncul
    0.34
     Concord
    0.33
    Act Density 0.019%

    No Known Activations