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

    Neuronpedia

    INDEX
    Explanations

    right

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Schmidt
    -0.07
     лік
    -0.07
    овани
    -0.07
     가지
    -0.06
    원이
    -0.06
     whistle
    -0.06
     Panama
    -0.06
     ochran
    -0.06
     OMIT
    -0.06
    _invoke
    -0.06
    POSITIVE LOGITS
     chiar
    0.07
    >>>
    0.07
    ęk
    0.06
    rsa
    0.06
    grade
    0.06
    Hon
    0.06
    usize
    0.06
    �u
    0.06
     každý
    0.06
     impeachment
    0.06
    Act Density 0.004%

    No Known Activations