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

    Neuronpedia

    INDEX
    Explanations

    sun setting

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases describing the sun’s movement at day’s end—e.g. sinking, setting, going below the horizon.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     exploited
    -0.07
     Withdraw
    -0.07
    serialization
    -0.07
    ointments
    -0.07
    _runner
    -0.07
    .Dark
    -0.06
     reject
    -0.06
    uname
    -0.06
     StringComparison
    -0.06
    Withdraw
    -0.06
    POSITIVE LOGITS
     انگلیسی
    0.06
    λμ
    0.06
     hoş
    0.06
     Veg
    0.06
    opup
    0.06
     ortadan
    0.06
     Morse
    0.06
     Compass
    0.05
     sep
    0.05
    gress
    0.05
    Act Density 0.006%

    No Known Activations