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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jeme
    -0.07
    .nc
    -0.07
    方案
    -0.06
    �
    -0.06
     اما
    -0.06
    erais
    -0.06
    ोलन
    -0.06
     WA
    -0.06
     tư
    -0.06
    Esc
    -0.06
    POSITIVE LOGITS
     sailed
    0.07
    maf
    0.07
     benefit
    0.07
    Rectangle
    0.07
    existing
    0.06
     slid
    0.06
    (display
    0.06
     scratching
    0.06
    He
    0.06
    DWORD
    0.06
    Act Density 0.014%

    No Known Activations