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

    Neuronpedia

    INDEX
    Explanations

    together

    np_max-act · gemini-2.0-flash

    The neuron specifically detects the word “together.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    [s
    -0.07
    n
    -0.07
    49
    -0.06
    rons
    -0.06
     snippet
    -0.06
    41
    -0.06
     Bronx
    -0.06
     Blood
    -0.06
    s
    -0.06
     indices
    -0.06
    POSITIVE LOGITS
     together
    0.15
     Together
    0.10
    Together
    0.10
     separating
    0.09
    gether
    0.09
    close
    0.08
     detach
    0.08
    잡
    0.08
    ighthouse
    0.07
    peak
    0.07
    Act Density 0.020%

    No Known Activations