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

    Neuronpedia

    INDEX
    Explanations

    Skipping forward

    np_max-act · gemini-2.0-flash

    The neuron activates on instructions or mentions of skipping—particularly the verb “skip” (e.g., “skip,” “skip ahead,” “skip the credits”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Vince
    -0.07
     Cir
    -0.07
     persuaded
    -0.07
     Corp
    -0.06
     Battlefield
    -0.06
     Bib
    -0.06
    Due
    -0.06
    _adj
    -0.06
     llama
    -0.06
     Levi
    -0.06
    POSITIVE LOGITS
    <message
    0.07
    562
    0.06
    -ln
    0.06
     Zones
    0.06
    Protected
    0.06
     directories
    0.06
    262
    0.06
     bash
    0.06
    uncate
    0.06
     sobě
    0.06
    Act Density 0.045%

    No Known Activations