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

    Neuronpedia

    INDEX
    Explanations

    words related to science and logical or mathematical constructs

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ora
    -0.06
    (s
    -0.06
    OOM
    -0.06
    uur
    -0.06
    nte
    -0.06
     Cout
    -0.06
    nde
    -0.06
    SError
    -0.06
    nis
    -0.06
     Levine
    -0.06
    POSITIVE LOGITS
    ioned
    0.08
     dÄ±ÅŁÄ±
    0.07
    aded
    0.07
    íģ¼
    0.07
    edly
    0.07
    fully
    0.07
    ght
    0.07
    irmed
    0.07
    ertino
    0.06
    tring
    0.06
    Act Density 0.143%

    No Known Activations