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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     undertake
    -0.07
     swim
    -0.06
     Grow
    -0.06
     harvest
    -0.06
     Axios
    -0.06
     Comcast
    -0.06
     buffalo
    -0.06
     eat
    -0.06
    ac
    -0.06
    exports
    -0.06
    POSITIVE LOGITS
     ανά
    0.07
    ّه
    0.06
    적
    0.06
     offending
    0.06
    landscape
    0.06
     TOP
    0.06
     ATTR
    0.06
     RECE
    0.06
    WAR
    0.06
    .poster
    0.06
    Act Density 0.016%

    No Known Activations