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

    Neuronpedia

    INDEX
    Explanations

    Code repositories

    np_max-act · gemini-2.0-flash

    The neuron detects long sequences of hexadecimal characters (e.g. git commit SHA identifiers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _frm
    -0.07
     Lens
    -0.07
     Brew
    -0.06
    ुण
    -0.06
    Purchase
    -0.06
    intree
    -0.06
     indication
    -0.06
     (_,
    -0.06
     Suzanne
    -0.06
     informant
    -0.06
    POSITIVE LOGITS
    抵
    0.07
    .JScrollPane
    0.07
     dataSnapshot
    0.06
     motto
    0.06
    aryawan
    0.06
    .closePath
    0.06
     BUG
    0.06
     Psalm
    0.06
    _LINE
    0.06
    BagConstraints
    0.06
    Act Density 0.011%

    No Known Activations