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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     factors
    -0.08
     этого
    -0.06
     předmět
    -0.06
     createdBy
    -0.06
     techn
    -0.06
    ющая
    -0.06
    leaders
    -0.06
     druh
    -0.06
     vešker
    -0.06
    jím
    -0.06
    POSITIVE LOGITS
     carving
    0.06
    avax
    0.06
     SAN
    0.06
     Liverpool
    0.06
     SAMPLE
    0.06
     Arte
    0.06
    -quality
    0.06
     lawn
    0.06
     replacing
    0.06
     Wonderful
    0.06
    Act Density 0.027%

    No Known Activations