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

    Neuronpedia

    INDEX
    Explanations

    island

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of islands.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Courtney
    -0.07
     viewPager
    -0.06
     Tomáš
    -0.06
     ntohs
    -0.06
     JE
    -0.06
    될
    -0.06
    Setter
    -0.06
     نماید
    -0.05
     ${
    -0.05
     Estates
    -0.05
    POSITIVE LOGITS
     liv
    0.07
    .temp
    0.07
    нав
    0.07
    -bin
    0.07
    (phi
    0.07
    933
    0.06
     arg
    0.06
    Μ
    0.06
    ď
    0.06
     narciss
    0.06
    Act Density 0.015%

    No Known Activations