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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Buddh
    -0.07
    >ID
    -0.07
    .=
    -0.07
     Midwest
    -0.07
     principalmente
    -0.06
     Emin
    -0.06
     verg
    -0.06
     tanın
    -0.06
     الفر
    -0.06
     Independ
    -0.06
    POSITIVE LOGITS
     Pipe
    0.06
     tuổi
    0.06
    Ав
    0.06
    лива
    0.06
     Txt
    0.06
    hz
    0.06
     Liga
    0.06
    bos
    0.06
    large
    0.06
     poisoning
    0.06
    Act Density 0.000%

    No Known Activations