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

    Neuronpedia

    INDEX
    Explanations

    reports and organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .solve
    -0.07
     Que
    -0.07
     embell
    -0.06
     πως
    -0.06
     Proposal
    -0.06
    ẫu
    -0.06
     Patterns
    -0.06
     Rep
    -0.06
     NN
    -0.06
     judging
    -0.06
    POSITIVE LOGITS
     useMemo
    0.06
     fiss
    0.06
    CEPTION
    0.06
    argent
    0.06
    purple
    0.06
    _legacy
    0.06
    /lists
    0.06
    �
    0.06
    _BLE
    0.06
     băng
    0.06
    Act Density 0.097%

    No Known Activations