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

    Neuronpedia

    INDEX
    Explanations

    while

    np_max-act · gemini-2.0-flash

    This neuron is effectively inactive and does not detect any patterns—it never activates.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     vyžad
    -0.06
    TextNode
    -0.06
    MS
    -0.06
    _listener
    -0.06
     slang
    -0.05
    ’h
    -0.05
    etsk
    -0.05
    'ya
    -0.05
     hdc
    -0.05
     iterating
    -0.05
    POSITIVE LOGITS
    .Animation
    0.08
    切
    0.07
     hosp
    0.07
    配合
    0.07
     align
    0.06
    WC
    0.06
     같은
    0.06
    ，与
    0.06
     今
    0.06
    ，没有
    0.06
    Act Density 0.037%

    No Known Activations