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

    Neuronpedia

    INDEX
    Explanations

    dropout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tableau
    0.48
    𝕒
    0.44
    𝕦
    0.44
    än
    0.42
     kab
    0.42
    ñ
    0.41
    ärm
    0.41
    ujo
    0.40
    rospective
    0.40
     pö
    0.40
    POSITIVE LOGITS
     Launch
    0.53
     Future
    0.51
     Idle
    0.50
     Foreground
    0.50
     Yin
    0.49
     लांच
    0.48
     Orphan
    0.48
     Perkin
    0.48
     Wanna
    0.47
     Licensed
    0.47
    Act Density 0.000%

    No Known Activations