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

    Neuronpedia

    INDEX
    Explanations

    ret

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on medical terms containing “ret” (e.g. retinal, retinopathy, subretinal).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Memory
    -0.07
     piss
    -0.07
     })
↵
    -0.07
     chứa
    -0.06
    _regeneration
    -0.06
    Recording
    -0.06
    ция
    -0.06
     allowances
    -0.06
    (Query
    -0.06
     dispro
    -0.06
    POSITIVE LOGITS
    ERICAN
    0.07
    وید
    0.06
     x
    0.06
    法国
    0.06
    .'"↵↵
    0.06
     hexadecimal
    0.06
    .friends
    0.06
     السعودية
    0.06
    -collapse
    0.06
    iв
    0.06
    Act Density 0.006%

    No Known Activations