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

    Neuronpedia

    INDEX
    Explanations

    scientific names

    np_max-act · gemini-2.0-flash

    The neuron specializes in detecting four-digit year tokens (publication dates) in species authority lines.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _tracks
    -0.07
     experiencia
    -0.06
    ند
    -0.06
     legality
    -0.06
    �
    -0.06
    ाल
    -0.06
    Formatted
    -0.06
    _pred
    -0.06
    _EP
    -0.06
     Hut
    -0.06
    POSITIVE LOGITS
    loi
    0.07
     ayak
    0.07
    “But
    0.06
     существ
    0.06
     introduce
    0.06
    .concatenate
    0.06
    并
    0.06
     besar
    0.06
     ввод
    0.06
    NPC
    0.06
    Act Density 0.004%

    No Known Activations