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

    Neuronpedia

    INDEX
    Explanations

    gentle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     приобрет
    -0.07
     roofing
    -0.06
     Adam
    -0.06
     score
    -0.06
     afr
    -0.06
    -find
    -0.06
     Ross
    -0.06
     limitless
    -0.06
     shard
    -0.06
     finds
    -0.06
    POSITIVE LOGITS
     gentle
    0.14
     gently
    0.12
     Gentle
    0.10
     gent
    0.07
     sympathetic
    0.07
     vaginal
    0.07
     лечения
    0.07
    MessageType
    0.07
    nte
    0.07
     commencement
    0.07
    Act Density 0.006%

    No Known Activations