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

    Neuronpedia

    INDEX
    Explanations

    underlying

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “underlying.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /********************************************************
    -0.07
    éra
    -0.07
    France
    -0.07
     nao
    -0.07
    事故
    -0.07
     manufactures
    -0.07
     cooper
    -0.07
     fer
    -0.06
    ='%
    -0.06
     PERFORMANCE
    -0.06
    POSITIVE LOGITS
     underlying
    0.13
     outline
    0.07
    Subsystem
    0.07
     underline
    0.07
    ิง
    0.06
    NSMutable
    0.06
    이
    0.06
    UNIT
    0.06
    व
    0.06
    Backend
    0.06
    Act Density 0.005%

    No Known Activations