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

    Neuronpedia

    INDEX
    Explanations

    maintaining uniqueness or focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    0.56
    colors
    0.52
    ց
    0.50
     minha
    0.46
    ц
    0.46
    ین
    0.46
    トリ
    0.46
    и
    0.45
    事項
    0.45
     पीले
    0.45
    POSITIVE LOGITS
     Nature
    0.54
    Streak
    0.54
     Streak
    0.51
     Kiev
    0.46
     Impulse
    0.46
    Newcastle
    0.44
    <unused2118>
    0.43
     Entropy
    0.43
     Addiction
    0.43
     Photoshop
    0.43
    Act Density 0.001%

    No Known Activations