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

    Neuronpedia

    INDEX
    Explanations

    fire

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wildfires
    0.66
     forests
    0.64
     bush
    0.63
     বন
    0.63
     वनस्प
    0.63
     rescues
    0.61
     forest
    0.60
     forested
    0.60
     wildflower
    0.60
    森林
    0.59
    POSITIVE LOGITS
     Nacht
    0.64
    Hand
    0.62
     Hand
    0.59
     hand
    0.55
     indirect
    0.55
     HAND
    0.54
     Indirect
    0.54
     Camin
    0.54
     retard
    0.54
     sling
    0.54
    Act Density 0.005%

    No Known Activations