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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outrage
    -0.07
    _SH
    -0.06
     persistence
    -0.06
     آل
    -0.06
    _zones
    -0.06
     resultado
    -0.06
     Fu
    -0.06
    Generated
    -0.06
    Calibri
    -0.06
     созда
    -0.06
    POSITIVE LOGITS
    렵
    0.08
    &C
    0.07
     poker
    0.07
    ПК
    0.06
    paths
    0.06
     autre
    0.06
    onder
    0.06
    ---@
    0.06
     misunderstood
    0.06
    utherland
    0.06
    Act Density 0.005%

    No Known Activations