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

    Neuronpedia

    INDEX
    Explanations

    At least one condition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thermal
    -0.08
     ARM
    -0.08
     gigante
    -0.08
     Angelina
    -0.08
    _ARM
    -0.08
     Tween
    -0.08
    orner
    -0.07
    aisin
    -0.07
    .arm
    -0.07
    .ar
    -0.07
    POSITIVE LOGITS
     shared
    0.14
    Shared
    0.13
    _SHARED
    0.13
    shared
    0.13
     साझा
    0.12
     gemeinsame
    0.12
     gemeinsamen
    0.11
    _shared
    0.11
     gemeins
    0.11
     Shared
    0.11
    Act Density 0.019%

    No Known Activations