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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron is effectively “dead” (it never activates on any tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Navbar
    -0.07
     suf
    -0.06
    茂
    -0.06
     Dost
    -0.06
    化
    -0.06
     mont
    -0.06
    Meter
    -0.06
     VIC
    -0.06
     Bast
    -0.06
    암
    -0.06
    POSITIVE LOGITS
    abis
    0.07
    角
    0.07
    rms
    0.07
    0
    0.07
    的一
    0.06
    .median
    0.06
     availability
    0.06
    attendance
    0.06
     sigmoid
    0.06
    收
    0.06
    Act Density 0.000%

    No Known Activations