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

    Neuronpedia

    INDEX
    Explanations

    onCreate method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     present
    0.74
     compromise
    0.72
     null
    0.71
     good
    0.70
     not
    0.67
     slow
    0.67
     world
    0.67
     textbook
    0.66
     forget
    0.66
     koj
    0.65
    POSITIVE LOGITS
    <unused652>
    0.75
    ఫో
    0.74
    htë
    0.72
    డా
    0.72
    స
    0.71
    funciones
    0.71
    しております
    0.70
    ത്തിയാ
    0.70
     armazenamento
    0.69
    सायन
    0.69
    Act Density 0.000%

    No Known Activations