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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron activates on first-person, self-referential words (I, my, we, etc.) indicating personal commentary.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    CLUDED
    -0.07
     Et
    -0.07
    Mutation
    -0.06
    imulation
    -0.06
     Entertainment
    -0.06
    mans
    -0.06
    319
    -0.06
    )::
    -0.06
    종
    -0.06
    Nat
    -0.06
    POSITIVE LOGITS
    ивают
    0.07
     Might
    0.07
    .LayoutStyle
    0.06
    ，本
    0.06
     би
    0.06
     طلا
    0.06
    .Java
    0.06
     элем
    0.06
    代码
    0.06
    СО
    0.05
    Act Density 0.099%

    No Known Activations