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

    Neuronpedia

    INDEX
    Explanations

    Actions

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on occurrences of the verb “take.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     will
    -0.10
     would
    -0.09
     must
    -0.09
     could
    -0.08
     doit
    -0.08
     WILL
    -0.08
    will
    -0.08
     might
    -0.07
    could
    -0.07
     may
    -0.07
    POSITIVE LOGITS
     sob
    0.07
    DSP
    0.07
    ，一
    0.07
     algum
    0.07
     bíl
    0.06
     TOM
    0.06
    ｜
    0.06
    cstring
    0.06
    -bl
    0.06
    แรง
    0.06
    Act Density 0.222%

    No Known Activations