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

    Neuronpedia

    INDEX
    Explanations

    complement

    np_max-act · gemini-2.0-flash

    This neuron detects words and phrases used to caution that a tool should be used alongside (not as a replacement for) other methods.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Assignable
    -0.07
     Sof
    -0.06
    STER
    -0.06
    .setUser
    -0.06
    brief
    -0.06
     sand
    -0.06
    /gtest
    -0.06
    /XMLSchema
    -0.06
     inplace
    -0.06
    ster
    -0.06
    POSITIVE LOGITS
    νι
    0.07
    logical
    0.07
     drifting
    0.06
    响
    0.06
    CharArray
    0.06
     ((__
    0.06
     الملك
    0.06
     keycode
    0.06
     harc
    0.06
    methodVisitor
    0.06
    Act Density 0.070%

    No Known Activations