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

    Neuronpedia

    INDEX
    Explanations

    prototype

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Josh
    -0.07
     multimedia
    -0.07
     Shift
    -0.06
     sum
    -0.06
    彼女
    -0.06
    Shared
    -0.06
     voices
    -0.06
     Josh
    -0.06
     Nx
    -0.06
    ษายน
    -0.06
    POSITIVE LOGITS
    名無し
    0.07
     prostitut
    0.07
    oplast
    0.07
    (startDate
    0.06
    وذ
    0.06
     olay
    0.06
     spiral
    0.06
     fq
    0.06
    history
    0.06
    .createElement
    0.06
    Act Density 0.002%

    No Known Activations