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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron never fires (all activations are zero), so it doesn’t detect any particular pattern—it’s effectively dead.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gat
    -0.07
     Ips
    -0.06
    INSTALL
    -0.06
     Ded
    -0.06
     infinite
    -0.06
     Mix
    -0.06
    Jun
    -0.06
    �
    -0.06
     enthus
    -0.06
     proh
    -0.06
    POSITIVE LOGITS
    edeki
    0.07
     belief
    0.07
     institution
    0.07
    .AddField
    0.07
     '_
    0.07
     CONTEXT
    0.07
    ляються
    0.06
    所属
    0.06
     fromDate
    0.06
     once
    0.06
    Act Density 0.043%

    No Known Activations