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

    Neuronpedia

    INDEX
    Explanations

    Rail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    िलत
    -0.07
    apesh
    -0.07
     contrato
    -0.07
    oleans
    -0.07
     ngủ
    -0.07
    ่ต
    -0.06
    -sh
    -0.06
     न
    -0.06
     výro
    -0.06
     Т
    -0.06
    POSITIVE LOGITS
     Rail
    0.13
     rail
    0.12
    Rail
    0.11
    ail
    0.07
    rail
    0.06
     SEAL
    0.06
     brit
    0.06
    ritz
    0.06
    ={`
    0.06
     Liu
    0.06
    Act Density 0.002%

    No Known Activations