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

    Neuronpedia

    INDEX
    Explanations

    gl

    np_max-act · gemini-2.0-flash

    This neuron activates on the substring “glut,” i.e. segments of scientific terms like “agglutination,” “glutaraldehyde,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     holdings
    -0.08
     Mutual
    -0.06
    _COMMAND
    -0.06
    ervention
    -0.06
     Alam
    -0.06
    -law
    -0.06
    ulpt
    -0.06
    .Identifier
    -0.06
    (std
    -0.06
    acterial
    -0.06
    POSITIVE LOGITS
     gracefully
    0.07
     unlink
    0.07
    řik
    0.07
     yıldır
    0.06
     pravděpodob
    0.06
     nộp
    0.06
     допомоги
    0.06
    çesi
    0.06
     weaken
    0.06
     LRV
    0.06
    Act Density 0.235%

    No Known Activations