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

    Neuronpedia

    INDEX
    Explanations

    portions

    np_max-act · gemini-2.0-flash

    the neuron detects mentions of quantities and portion‐size indicators (e.g. “portions,” numeric amounts, “large,” “side,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Judge
    -0.07
    (Edit
    -0.06
    chop
    -0.06
     Classified
    -0.06
    Login
    -0.06
     Wolves
    -0.06
    داشت
    -0.06
     رف
    -0.06
     RULE
    -0.06
    ded
    -0.06
    POSITIVE LOGITS
    .sd
    0.07
    (xx
    0.07
    -----------*/↵
    0.07
     všichni
    0.06
     εισ
    0.06
    -j
    0.06
    (ListNode
    0.06
    ]>
    0.06
     ==============================================================
    0.06
     (${
    0.06
    Act Density 0.010%

    No Known Activations