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

    Neuronpedia

    INDEX
    Explanations

    additional information

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “something.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    া�
    -0.07
     REQUIRED
    -0.06
     underscore
    -0.06
     groom
    -0.06
    rays
    -0.06
    摘要
    -0.06
     Jose
    -0.06
    _DOMAIN
    -0.06
     demonstrates
    -0.06
    requires
    -0.06
    POSITIVE LOGITS
     Liver
    0.07
    .jetbrains
    0.07
    (move
    0.07
     textile
    0.06
    /kubernetes
    0.06
    .inspect
    0.06
     감사
    0.06
    ceae
    0.06
     Григор
    0.06
    _BOOLEAN
    0.06
    Act Density 0.003%

    No Known Activations