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

    Neuronpedia

    INDEX
    Explanations

    explore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -negative
    -0.08
    _ENDIAN
    -0.07
     canc
    -0.06
     stain
    -0.06
     beaten
    -0.06
     noisy
    -0.06
    note
    -0.06
    ився
    -0.06
     gigantic
    -0.06
     trick
    -0.06
    POSITIVE LOGITS
     explore
    0.13
     explored
    0.12
     exploring
    0.11
     explores
    0.11
     explorer
    0.09
     Explore
    0.08
     Explorer
    0.08
     exploration
    0.08
    探
    0.08
    交流
    0.08
    Act Density 0.024%

    No Known Activations