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

    Neuronpedia

    INDEX
    Explanations

    keywords followed by parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    0.61
    р
    0.59
    ان
    0.57
    ים
    0.57
    屑
    0.57
    りたい
    0.51
    ाइन
    0.50
    ε
    0.49
    oler
    0.49
    ㈠
    0.49
    POSITIVE LOGITS
    ছিল
    0.51
     непри
    0.47
    >
    0.47
     anonymously
    0.45
    }
    0.45
    မြ
    0.44
     hyperfine
    0.44
    ನಿಯ
    0.44
     Quark
    0.43
     at
    0.43
    Act Density 0.000%

    No Known Activations