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

    Neuronpedia

    INDEX
    Explanations

    animals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aries
    -0.50
    ients
    -0.49
    vity
    -0.46
    als
    -0.44
    ρω
    -0.44
     kasarigan
    -0.43
     JFrame
    -0.43
    teht
    -0.43
     vux
    -0.41
    oves
    -0.41
    POSITIVE LOGITS
    girl
    0.75
    catcher
    0.70
    prince
    0.69
    hunter
    0.69
    herd
    0.68
    child
    0.67
    boy
    0.66
    god
    0.64
    whisper
    0.64
    man
    0.63
    Act Density 0.007%

    No Known Activations