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

    Neuronpedia

    INDEX
    Explanations

    lor

    np_max-act · gemini-2.0-flash

    This neuron detects scientific terms beginning with the “chlor-” prefix (e.g. chloroplast, chloride, chlorotoxin, chlorinated, chlorpromazine, chlorodeoxyadenosine, chlorhexidine).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     groundwork
    -0.07
    tega
    -0.07
    vek
    -0.07
    ựa
    -0.07
    ovaly
    -0.07
    .addNode
    -0.07
     ava
    -0.07
     passage
    -0.07
    vv
    -0.07
    емых
    -0.07
    POSITIVE LOGITS
     Chlor
    0.12
     chlor
    0.11
    chlor
    0.10
     chlorine
    0.09
     chloride
    0.08
    Platform
    0.07
    示
    0.07
     Clipboard
    0.07
    DROP
    0.07
     Chronic
    0.07
    Act Density 0.014%

    No Known Activations