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

    Neuronpedia

    INDEX
    Explanations

    keyboards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     publishing
    -0.07
     bullet
    -0.06
     congressman
    -0.06
    ighbor
    -0.06
     Clock
    -0.06
    ้าท
    -0.06
    Tab
    -0.06
    curso
    -0.06
     Release
    -0.06
     compra
    -0.06
    POSITIVE LOGITS
     erotica
    0.06
    mobx
    0.06
     später
    0.06
     /////
    0.06
     fertility
    0.06
     LONG
    0.06
     models
    0.06
    urtle
    0.06
     violently
    0.06
     jLabel
    0.06
    Act Density 0.029%

    No Known Activations