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

    Neuronpedia

    INDEX
    Explanations

    harvest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <char
    -0.07
     swearing
    -0.07
    (go
    -0.07
     drag
    -0.07
    nic
    -0.07
     irrational
    -0.07
    _STATE
    -0.07
     canine
    -0.07
     Coord
    -0.06
     政
    -0.06
    POSITIVE LOGITS
     harvesting
    0.11
     harvest
    0.11
     Harvest
    0.09
     harvested
    0.07
     Sample
    0.07
    .defaultValue
    0.06
     hybrid
    0.06
     Harvey
    0.06
    SAVE
    0.06
     hunter
    0.06
    Act Density 0.011%

    No Known Activations