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

    Neuronpedia

    INDEX
    Explanations

    post

    np_max-act · gemini-2.0-flash

    This neuron responds to the prefix “post-” in hyphenated terms (e.g. “post-2015,” “post-9/11,” “post-shuttle”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _:*
    -0.07
    ughty
    -0.07
     anatom
    -0.07
    Recommended
    -0.06
     triangular
    -0.06
     Trigger
    -0.06
     Married
    -0.06
     doubles
    -0.06
    .dispose
    -0.06
     mạnh
    -0.06
    POSITIVE LOGITS
    .fire
    0.07
     initialState
    0.06
    �
    0.06
    (cs
    0.06
    平成
    0.06
    ╝
    0.06
    후기
    0.06
    /edit
    0.06
    Return
    0.06
     postings
    0.06
    Act Density 0.010%

    No Known Activations