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

    Neuronpedia

    INDEX
    Explanations

    male

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     authService
    -0.07
    sessionId
    -0.07
     telefon
    -0.07
     מתחת
    -0.06
    ELSE
    -0.06
    /render
    -0.06
    -sl
    -0.06
     środk
    -0.06
    imitive
    -0.06
    تاريخ
    -0.06
    POSITIVE LOGITS
     ARM
    0.07
     growth
    0.06
    ières
    0.06
    れば
    0.06
    旺
    0.06
     JAN
    0.06
    .groupControl
    0.06
     leve
    0.06
    ︶
    0.06
    LLLL
    0.06
    Act Density 0.000%

    No Known Activations