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

    Neuronpedia

    INDEX
    Explanations

    Union

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     catastrophe
    -0.07
    Chris
    -0.07
    ittance
    -0.06
    ście
    -0.06
    pte
    -0.06
    晚
    -0.06
    RITE
    -0.06
     toda
    -0.06
    Steve
    -0.06
     Steve
    -0.06
    POSITIVE LOGITS
     Union
    0.11
     union
    0.09
    Union
    0.09
     Jacob
    0.08
     rematch
    0.08
    ion
    0.08
    connector
    0.07
     UNION
    0.07
    Neither
    0.07
    ins
    0.07
    Act Density 0.010%

    No Known Activations