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

    Neuronpedia

    INDEX
    Explanations

    those

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Americans
    -0.07
     Americans
    -0.06
     COMMIT
    -0.06
     arrang
    -0.06
     Existing
    -0.06
     ensuite
    -0.06
    eses
    -0.06
    album
    -0.06
     records
    -0.06
     Lyons
    -0.06
    POSITIVE LOGITS
    Dock
    0.07
    BitFields
    0.06
    sgi
    0.06
     erotique
    0.06
    Tr
    0.06
    mol
    0.06
     Decomp
    0.06
     �
    0.06
    حيح
    0.06
     الخط
    0.06
    Act Density 0.082%

    No Known Activations