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

    Neuronpedia

    INDEX
    Explanations

    observer

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of “observer” (including inter-observer, intra-observer, and related reproducibility terms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     kin
    -0.07
     hobby
    -0.06
     Zones
    -0.06
    869
    -0.06
    .bad
    -0.06
    ebek
    -0.06
     coursework
    -0.06
     lamb
    -0.06
    tracks
    -0.06
     XL
    -0.06
    POSITIVE LOGITS
    _RIGHT
    0.08
     фунда
    0.07
    .GL
    0.07
    leshoot
    0.07
    exao
    0.07
    tere
    0.07
    formation
    0.07
    queues
    0.07
    riba
    0.07
    iphers
    0.06
    Act Density 0.010%

    No Known Activations