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

    Neuronpedia

    INDEX
    Explanations

    configuration steps

    np_max-act · gemini-2.0-flash

    This neuron flags imperative step‐heading verbs in how-to instructions (e.g. “Identify,” “Download,” “Install”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    edo
    -0.07
    .githubusercontent
    -0.06
    год
    -0.06
    FixedSize
    -0.06
    <form
    -0.06
    Jan
    -0.06
     polymer
    -0.06
     INNER
    -0.05
    .mode
    -0.05
     spinal
    -0.05
    POSITIVE LOGITS
     Bathroom
    0.07
    گه
    0.07
    AndPassword
    0.07
    _associ
    0.07
     confession
    0.06
     encountering
    0.06
    ยนตร
    0.06
     최대
    0.06
    compare
    0.06
    urgy
    0.06
    Act Density 0.330%

    No Known Activations