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

    Neuronpedia

    INDEX
    Explanations

    help/assistance resources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MSG
    -0.07
    ules
    -0.07
     seismic
    -0.07
    -facebook
    -0.07
    UU
    -0.06
     assaults
    -0.06
     nghị
    -0.06
     MPEG
    -0.06
    _raises
    -0.06
     violent
    -0.06
    POSITIVE LOGITS
     nedost
    0.06
     unto
    0.06
     amor
    0.06
    186
    0.06
     Routing
    0.06
    .amazonaws
    0.06
    (foo
    0.06
    CHEMY
    0.06
     obrig
    0.06
     عالية
    0.06
    Act Density 0.090%

    No Known Activations