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

    Neuronpedia

    INDEX
    Explanations

    business and operations

    np_max-act · gemini-2.0-flash

    The neuron fires on domain-specific key nouns—names of tools, components, roles, or concepts—that introduce or label a particular topic.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     portion
    -0.07
     Gods
    -0.07
    іг
    -0.06
    rawing
    -0.06
    Crear
    -0.06
    ीन
    -0.06
    .Connection
    -0.06
     Initialized
    -0.06
     portions
    -0.06
     віднов
    -0.06
    POSITIVE LOGITS
     getProduct
    0.06
     KNOW
    0.06
     chac
    0.06
     Porno
    0.06
    MET
    0.06
    OLS
    0.06
     deeply
    0.06
    ﻠ
    0.06
    森
    0.06
     quả
    0.06
    Act Density 0.154%

    No Known Activations