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

    Neuronpedia

    INDEX
    Explanations

    too

    np_max-act · gemini-2.0-flash

    This neuron detects the intensifier “too.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gösteren
    -0.07
    -page
    -0.07
     Hend
    -0.07
    assert
    -0.07
    -bind
    -0.07
    -ph
    -0.07
     scl
    -0.07
    chemical
    -0.06
     agents
    -0.06
    VertexAttribArray
    -0.06
    POSITIVE LOGITS
     too
    0.18
     Too
    0.13
     TOO
    0.13
    too
    0.12
    Too
    0.11
    -too
    0.09
    oo
    0.09
    u
    0.08
    OO
    0.08
     Tou
    0.07
    Act Density 0.018%

    No Known Activations