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

    Neuronpedia

    INDEX
    Explanations

    interpersonal relationships

    np_max-act · gemini-2.0-flash

    This neuron detects Portuguese words related to sharing or being together (e.g., “compartilhar,” “juntas”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tricky
    -0.07
     Cass
    -0.07
    proxy
    -0.06
     fluores
    -0.06
     corn
    -0.06
    Resolver
    -0.06
     indu
    -0.06
    trees
    -0.06
    .sat
    -0.06
    -corner
    -0.06
    POSITIVE LOGITS
     share
    0.07
     obchod
    0.06
    ßer
    0.06
    으며
    0.06
    ltk
    0.06
     objetivo
    0.06
     paylaş
    0.06
    okoj
    0.06
    .getError
    0.06
    .ContentAlignment
    0.06
    Act Density 0.018%

    No Known Activations