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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations and names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     established
    -0.06
    toc
    -0.06
     miglior
    -0.06
    uentes
    -0.06
     escalated
    -0.06
     increases
    -0.06
    (isset
    -0.06
    官方
    -0.06
     debido
    -0.06
    )/
    -0.06
    POSITIVE LOGITS
     нач
    0.07
     على
    0.06
    arie
    0.06
    (GameObject
    0.06
     invokingState
    0.06
    _EXEC
    0.06
    osloven
    0.06
    :maj
    0.06
     :|
    0.06
     disappointing
    0.06
    Act Density 0.026%

    No Known Activations