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

    Neuronpedia

    INDEX
    Explanations

    their

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ra
    -0.07
     Judaism
    -0.07
    珕
    -0.07
    既
    -0.06
    Essay
    -0.06
    (pa
    -0.06
    -it
    -0.06
    𝓯
    -0.06
    𓇼
    -0.06
    嘧
    -0.06
    POSITIVE LOGITS
    ichael
    0.08
    �
    0.07
    ODE
    0.07
    👀
    0.07
    _Module
    0.07
     folder
    0.07
    Welcome
    0.07
     ()=>{↵
    0.07
    水质
    0.07
    apsed
    0.07
    Act Density 0.067%

    No Known Activations