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

    Neuronpedia

    INDEX
    Explanations

    **Title: **

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     généralement
    0.69
     일반적으로
    0.67
     frequently
    0.66
     және
    0.65
     characteristics
    0.64
     рекомендуется
    0.63
     usually
    0.62
     ఇతర
    0.62
     commonly
    0.62
     매우
    0.62
    POSITIVE LOGITS
     Shadows
    0.80
     Time
    0.76
     Terror
    0.74
    Terror
    0.74
    Shadow
    0.73
     Shadow
    0.72
    Ghosts
    0.71
     Fear
    0.69
     Silence
    0.69
     Beyond
    0.68
    Act Density 0.036%

    No Known Activations