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

    Neuronpedia

    INDEX
    Explanations

    qualities or characteristics

    np_max-act · gemini-2.0-flash

    This neuron detects nominalizations ending in “-ment.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     antibiotics
    -0.07
     chill
    -0.06
    lx
    -0.06
     hips
    -0.06
    네
    -0.06
     newSize
    -0.06
    ा.
    -0.06
    шила
    -0.06
     paypal
    -0.06
    ন
    -0.06
    POSITIVE LOGITS
     GUID
    0.07
    "D
    0.07
    Muon
    0.06
     fakt
    0.06
     Optionally
    0.06
    .Business
    0.06
    idunt
    0.06
    JR
    0.06
     Bond
    0.06
    ;;↵↵
    0.06
    Act Density 0.065%

    No Known Activations