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

    Neuronpedia

    INDEX
    Explanations

    posable

    np_max-act · gemini-2.0-flash

    The neuron responds to words related to transposable elements, specifically those containing the “transpos” stem (e.g., “transposable,” “transposition,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    leground
    -0.07
     ruins
    -0.07
     Married
    -0.07
    .gg
    -0.06
    .emf
    -0.06
    .weights
    -0.06
     beef
    -0.06
     whence
    -0.06
     Salvador
    -0.06
    还有
    -0.06
    POSITIVE LOGITS
    Respons
    0.06
    σιμοποι
    0.06
    (cube
    0.06
     Platform
    0.06
     груп
    0.06
     tidy
    0.06
     لع
    0.06
     ],↵↵
    0.06
     cooperate
    0.06
     الخاص
    0.06
    Act Density 0.002%

    No Known Activations