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

    Neuronpedia

    INDEX
    Explanations

    VALUES

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on SQL INSERT ... VALUES clauses and the numeric literals within them.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cet
    -0.07
     proposed
    -0.06
     esk
    -0.06
    .green
    -0.06
    чес
    -0.06
    ولة
    -0.06
    动物
    -0.06
    итися
    -0.06
    apg
    -0.06
     Kaf
    -0.06
    POSITIVE LOGITS
    parallel
    0.07
    टर
    0.06
    Remarks
    0.06
     entries
    0.06
     reclaim
    0.06
    raison
    0.06
     Victoria
    0.06
    Clazz
    0.06
    _choose
    0.06
    �
    0.06
    Act Density 0.004%

    No Known Activations