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

    Neuronpedia

    INDEX
    Explanations

    weather and geography

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wave
    1.50
     waves
    1.49
     clouds
    1.42
     Wave
    1.41
     Waves
    1.38
    Wave
    1.36
     Clouds
    1.34
     volcanic
    1.30
     Wind
    1.29
     tide
    1.29
    POSITIVE LOGITS
     nursing
    0.77
    neq
    0.71
     lipstick
    0.69
     gymnast
    0.68
    #__
    0.66
    ạp
    0.66
     emptying
    0.66
    mass
    0.64
     masses
    0.64
     pajamas
    0.63
    Act Density 0.247%

    No Known Activations