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

    Neuronpedia

    INDEX
    Explanations

    article/preposition

    np_max-act · gemini-2.0-flash

    The neuron never activates on any token—it appears effectively “dead” and does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     каз
    -0.07
     生命周期函数
    -0.06
    AM
    -0.06
     συμβ
    -0.06
    .ErrorCode
    -0.06
     SPEC
    -0.06
     ed
    -0.06
    �
    -0.06
     involving
    -0.06
    (".",
    -0.06
    POSITIVE LOGITS
     ntohs
    0.07
     tranny
    0.07
    weathermap
    0.06
    ,in
    0.06
    ierarchy
    0.06
    exampleModalLabel
    0.06
    ogeneity
    0.06
     Proble
    0.06
     GTK
    0.06
     splice
    0.06
    Act Density 0.027%

    No Known Activations