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

    Neuronpedia

    INDEX
    Explanations

    .xml

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    よび
    -0.07
    .pres
    -0.07
     accru
    -0.06
     norms
    -0.06
    ansion
    -0.06
     heroin
    -0.06
    distance
    -0.06
     rex
    -0.06
     확
    -0.06
    yntaxException
    -0.06
    POSITIVE LOGITS
     Hanging
    0.07
    جل
    0.07
     Understand
    0.07
     específ
    0.06
    UNG
    0.06
     tumult
    0.06
    غل
    0.06
    стер
    0.06
     ग
    0.06
    icy
    0.06
    Act Density 0.001%

    No Known Activations