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

    Neuronpedia

    INDEX
    Explanations

    offset

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the term “offset.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    14
    -0.07
     Mann
    -0.07
     Mare
    -0.07
    (game
    -0.07
    .tabPage
    -0.07
    _py
    -0.07
     compose
    -0.06
    ,UnityEngine
    -0.06
    _CREATE
    -0.06
    charm
    -0.06
    POSITIVE LOGITS
     offset
    0.11
    offset
    0.10
    Offset
    0.09
    (offset
    0.08
    	offset
    0.08
    focused
    0.08
     Од
    0.08
     OFFSET
    0.07
    et
    0.07
     Insets
    0.07
    Act Density 0.005%

    No Known Activations