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

    Neuronpedia

    INDEX
    Explanations

    linear transformations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lof
    -0.08
    提示
    -0.08
    solutions
    -0.08
    Instructions
    -0.07
    LO
    -0.07
    ina
    -0.07
     साहित्य
    -0.07
    Solutions
    -0.07
    ophe
    -0.07
    anine
    -0.07
    POSITIVE LOGITS
     maps
    0.11
    .maps
    0.08
     hashmap
    0.08
     Runnable
    0.08
     Yon
    0.08
     mapa
    0.08
     katal
    0.08
     claiming
    0.08
     Schatten
    0.08
     mapas
    0.08
    Act Density 0.011%

    No Known Activations