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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thesis
    -0.07
    lation
    -0.07
     Tokens
    -0.07
     AssertionError
    -0.07
    の一
    -0.07
     unreachable
    -0.07
    ]))
    -0.07
    Failed
    -0.07
    Fonts
    -0.06
     Ingredient
    -0.06
    POSITIVE LOGITS
     kuk
    0.06
     objekt
    0.06
     osobní
    0.06
     thậm
    0.06
     regress
    0.06
    sponsor
    0.06
     Baltic
    0.06
     Trab
    0.06
     فعالیت
    0.06
     nulla
    0.06
    Act Density 0.118%

    No Known Activations