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

    Neuronpedia

    INDEX
    Explanations

    compet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rin
    -0.07
     Narrow
    -0.07
     doubtful
    -0.07
     Zahl
    -0.06
    nivel
    -0.06
    (sign
    -0.06
    стве
    -0.06
    row
    -0.06
     lapse
    -0.06
     caut
    -0.06
    POSITIVE LOGITS
    .''
    0.07
    -ne
    0.07
    eliness
    0.07
    ecycle
    0.07
    .gms
    0.06
    Party
    0.06
    .Socket
    0.06
    平台
    0.06
     خدمت
    0.06
    .ResultSet
    0.06
    Act Density 0.006%

    No Known Activations