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

    Neuronpedia

    INDEX
    Explanations

    demon subtly, beyond death

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    にか
    0.52
    leading
    0.51
    ↵↵
    0.50
     e
    0.49
     =
    0.48
        
    0.46
    )
    0.46
    ．
    0.46
    .
    0.45
    0.44
    POSITIVE LOGITS
     ದೊಡ್ಡ
    0.52
    žev
    0.51
    ܘܢ
    0.50
     outings
    0.48
    erequisite
    0.48
    ᴙ
    0.48
    铷
    0.48
    㓦
    0.48
    нский
    0.47
     జరిగిన
    0.47
    Act Density 0.000%

    No Known Activations