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

    Neuronpedia

    INDEX
    Explanations

    references to different types of flooring or surfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "floor" and its related contexts

    np_acts-logits-general · gemini-2.0-flash

    floor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    повід
    -0.56
    }^{*}
    -0.52
    thenReturn
    -0.52
    matitis
    -0.51
     pear
    -0.50
    eev
    -0.49
     kans
    -0.49
    oué
    -0.49
     majority
    -0.49
    geven
    -0.48
    POSITIVE LOGITS
    GraphicsUnit
    1.11
     Floors
    0.97
     Floor
    0.94
     FLOOR
    0.88
    floors
    0.88
    FLOOR
    0.86
     floors
    0.84
    floor
    0.81
     незавершена
    0.81
    Floor
    0.81
    Act Density 0.150%

    No Known Activations