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

    Neuronpedia

    INDEX
    Explanations

    offset

    np_max-act · gemini-2.0-flash

    It detects parameter‐setting words in code comments or docs—especially terms like “ADJUSTMENT,” “offset,” “height,” and other numeric configuration names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    edo
    -0.06
     Mundo
    -0.06
     cùng
    -0.06
     короб
    -0.06
    _survey
    -0.06
    emas
    -0.06
    editar
    -0.06
    .Label
    -0.06
    .scenes
    -0.06
    け
    -0.06
    POSITIVE LOGITS
     �
    0.07
     power
    0.06
    =df
    0.06
    长
    0.06
     города
    0.06
    jie
    0.06
     brains
    0.06
    (dm
    0.06
     grief
    0.06
     diy
    0.06
    Act Density 0.032%

    No Known Activations