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

    Neuronpedia

    INDEX
    Explanations

    Before-bed advice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     concluded
    -0.08
    مكون
    -0.07
     selves
    -0.07
     Cock
    -0.07
    cka
    -0.07
    /F
    -0.07
     reflects
    -0.06
     Co
    -0.06
    oday
    -0.06
    INCLUDING
    -0.06
    POSITIVE LOGITS
    _FRIEND
    0.07
    抗震
    0.07
    猫咪
    0.07
    Gallery
    0.07
     לעבור
    0.06
    ～
    0.06
     Silent
    0.06
    海南
    0.06
    ի
    0.06
    经商
    0.06
    Act Density 0.011%

    No Known Activations