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

    Neuronpedia

    INDEX
    Explanations

    specific topic or situation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CCSD
    0.47
     profound
    0.44
     intenso
    0.44
     acteur
    0.44
    sete
    0.44
     avrebbe
    0.43
     rolle
    0.43
    expression
    0.42
    älte
    0.41
    يرة
    0.41
    POSITIVE LOGITS
     휴
    0.42
     ഇഷ്ട
    0.40
     никаких
    0.40
     बाकी
    0.39
     ।,
    0.39
    命
    0.39
     просмо
    0.39
     thumbnails
    0.38
     하기
    0.38
     ।
    0.38
    Act Density 0.001%

    No Known Activations