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

    Neuronpedia

    INDEX
    Explanations

    Degrees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Amount
    -0.07
    часно
    -0.06
    .cr
    -0.06
     Allan
    -0.06
     annihil
    -0.06
     occurring
    -0.06
    icana
    -0.06
    міні
    -0.06
    nim
    -0.06
    的事情
    -0.06
    POSITIVE LOGITS
    cor
    0.07
     Savage
    0.07
     Gre
    0.07
     Dre
    0.07
    :pointer
    0.06
     overriding
    0.06
     Department
    0.06
     Typical
    0.06
     Guess
    0.06
     GK
    0.06
    Act Density 0.005%

    No Known Activations