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

    Neuronpedia

    INDEX
    Explanations

    Proportions

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on the token “sunshine,” i.e. it detects mentions of sunshine.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Columbia
    -0.07
     Journal
    -0.06
    .isEmpty
    -0.06
     FR
    -0.06
    .Resources
    -0.06
     Jog
    -0.06
    .portal
    -0.06
     in
    -0.06
    ��
    -0.06
     Centro
    -0.06
    POSITIVE LOGITS
     оно
    0.07
     DEVICE
    0.06
    开始
    0.06
    angan
    0.06
    รงเร
    0.06
    basePath
    0.06
     constituency
    0.06
     recognition
    0.06
    隐
    0.06
    一定
    0.06
    Act Density 0.001%

    No Known Activations