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

    Neuronpedia

    INDEX
    Explanations

    -effects

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the word “effects,” especially the “-effects” in “random-effects model” phrasing typical of meta-analysis methods.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     baked
    -0.08
    肃
    -0.07
     Peyton
    -0.07
     网
    -0.07
     快
    -0.06
     Minneapolis
    -0.06
    LAN
    -0.06
    (zone
    -0.06
     pian
    -0.06
    Nd
    -0.06
    POSITIVE LOGITS
     setName
    0.07
    สำหร
    0.06
    -sync
    0.06
     textStatus
    0.06
     Reflect
    0.06
    .readFile
    0.06
    _show
    0.06
    .DataGridViewCellStyle
    0.06
     книж
    0.06
    _pll
    0.06
    Act Density 0.001%

    No Known Activations