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

    Neuronpedia

    INDEX
    Explanations

    together

    np_max-act · gemini-2.0-flash

    The neuron spots descriptions of mechanical connections—verbs and phrasing that indicate parts being fastened, hinged, welded, overlapped, or otherwise joined together.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     larg
    -0.06
    .depth
    -0.06
    D
    -0.06
     dài
    -0.06
    umlu
    -0.06
    prevState
    -0.06
     egret
    -0.06
    ал
    -0.06
     favorite
    -0.06
     숨
    -0.06
    POSITIVE LOGITS
     Machinery
    0.07
    Facing
    0.07
     Infer
    0.07
     Continental
    0.06
     Engineers
    0.06
    locking
    0.06
    ROT
    0.06
    orneys
    0.06
     compose
    0.06
     VIN
    0.06
    Act Density 0.012%

    No Known Activations