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

    Neuronpedia

    INDEX
    Explanations

    Labrador

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DEBUG
    -0.07
     tái
    -0.07
     komm
    -0.07
     prepend
    -0.07
    _ask
    -0.07
     ngủ
    -0.07
     decorate
    -0.07
    fffffff
    -0.07
    ⌒
    -0.07
    	remove
    -0.07
    POSITIVE LOGITS
     Robert
    0.07
     Entertainment
    0.07
    𝕷
    0.07
     sill
    0.07
    名列前
    0.07
    Capability
    0.06
     corruption
    0.06
     least
    0.06
    ment
    0.06
     Imperial
    0.06
    Act Density 0.001%

    No Known Activations