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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    回国
    -0.08
    ȅ
    -0.08
    在意
    -0.07
    adians
    -0.07
    來自
    -0.06
    七八
    -0.06
    invert
    -0.06
    getJSON
    -0.06
    ields
    -0.06
    מדריך
    -0.06
    POSITIVE LOGITS
     Monitoring
    0.08
     Kick
    0.08
     knots
    0.07
    ubb
    0.07
    (found
    0.07
    controller
    0.07
    无障碍
    0.07
     محم
    0.07
    	ps
    0.07
     PLL
    0.07
    Act Density 0.000%

    No Known Activations