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

    Neuronpedia

    INDEX
    Explanations

    Andes mountains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    础
    0.43
     użyt
    0.42
    ⾃
    0.40
     technique
    0.38
    الہ
    0.38
    静态
    0.37
    宾
    0.37
     tár
    0.37
    seud
    0.37
     başlayalım
    0.37
    POSITIVE LOGITS
     expedit
    0.48
    andidates
    0.47
    nader
    0.47
    ailangan
    0.45
     genotypes
    0.45
    ।.
    0.45
     कोणी
    0.44
     사망
    0.44
     bisexual
    0.43
     assurances
    0.43
    Act Density 0.002%

    No Known Activations