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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    andReturn
    -0.07
    ्यम
    -0.06
     jste
    -0.06
     striving
    -0.06
    물을
    -0.06
     gerektir
    -0.06
     jiných
    -0.06
     print
    -0.06
     downright
    -0.06
    -pill
    -0.06
    POSITIVE LOGITS
    最終
    0.07
     frog
    0.06
    swift
    0.06
     commitments
    0.06
    .Can
    0.06
    /↵↵↵
    0.06
     sig
    0.06
    /test
    0.06
     Prepare
    0.06
     Forms
    0.06
    Act Density 0.000%

    No Known Activations