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

    Neuronpedia

    INDEX
    Explanations

    components

    np_max-act · gemini-2.0-flash

    The neuron activates on technical product‐specification terms referring to physical parts or components (e.g. channel, edge, swing, heads, socket, wire, swivel).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    年に
    -0.06
    ]['
    -0.06
    ��
    -0.06
     "")↵↵
    -0.06
     куб
    -0.06
    其他
    -0.06
    passes
    -0.06
    营
    -0.06
     Peng
    -0.06
    慎
    -0.06
    POSITIVE LOGITS
    nostic
    0.07
    Fore
    0.07
    _IMM
    0.06
     luckily
    0.06
     Stuart
    0.06
     scientific
    0.06
     modulation
    0.06
     그래서
    0.06
    .velocity
    0.06
     capital
    0.06
    Act Density 0.047%

    No Known Activations