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

    Neuronpedia

    INDEX
    Explanations

    obtain

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric values, especially decimal numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     crisis
    -0.07
     Disk
    -0.07
     channel
    -0.07
     wave
    -0.07
     driver
    -0.07
     race
    -0.07
     plays
    -0.07
     flipped
    -0.07
     face
    -0.06
     buzz
    -0.06
    POSITIVE LOGITS
     obtained
    0.12
     obtain
    0.11
     obtaining
    0.10
     Obtain
    0.10
     Obt
    0.09
     obtains
    0.09
    ohn
    0.08
     حاصل
    0.08
     obten
    0.08
    OTT
    0.08
    Act Density 0.026%

    No Known Activations