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

    Neuronpedia

    INDEX
    Explanations

    down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pří
    -0.07
     FIFO
    -0.07
     energetic
    -0.07
     吉
    -0.07
     nec
    -0.07
    ěk
    -0.06
    if
    -0.06
     Ci
    -0.06
    fraction
    -0.06
     Alic
    -0.06
    POSITIVE LOGITS
     Down
    0.14
     down
    0.13
    down
    0.11
     DOWN
    0.10
    .Down
    0.10
    Down
    0.10
    DOWN
    0.09
    _DOWN
    0.09
    markdown
    0.09
    shutdown
    0.09
    Act Density 0.044%

    No Known Activations