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

    Neuronpedia

    INDEX
    Explanations

    modify

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    INCLUDE
    -0.07
    掛
    -0.07
     высокой
    -0.07
     cmdline
    -0.07
    ầ
    -0.06
    �
    -0.06
    Glass
    -0.06
     Dank
    -0.06
    าซ
    -0.06
     addButton
    -0.06
    POSITIVE LOGITS
    ................
    0.07
    овые
    0.06
     turn
    0.06
     повинна
    0.06
     cog
    0.06
     paths
    0.06
    vince
    0.06
    =http
    0.06
    .receive
    0.06
    onents
    0.06
    Act Density 0.008%

    No Known Activations