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

    Neuronpedia

    INDEX
    Explanations

    inlet

    np_max-act · gemini-2.0-flash

    This neuron detects references to inlet passages (the word “inlet”) in technical descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ℃
    -0.07
    ’es
    -0.07
    Videos
    -0.07
     errmsg
    -0.07
    ána
    -0.07
    igidBody
    -0.07
    .gs
    -0.06
    Africa
    -0.06
    =models
    -0.06
     posto
    -0.06
    POSITIVE LOGITS
     inlet
    0.08
     når
    0.07
     </
    0.06
     маль
    0.06
    !</
    0.06
     reve
    0.06
     пре
    0.06
     levy
    0.06
    reetings
    0.06
     ánh
    0.06
    Act Density 0.004%

    No Known Activations