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

    Neuronpedia

    INDEX
    Explanations

    institutional context and framework

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comforted
    0.39
     disregarding
    0.39
     دوا
    0.38
     জি
    0.37
     сне
    0.37
     zwe
    0.37
     whiche
    0.37
    ventus
    0.36
    0.36
     Resting
    0.36
    POSITIVE LOGITS
     text
    0.61
    text
    0.56
    Text
    0.51
     Text
    0.42
     tekst
    0.41
     texture
    0.41
    촉
    0.40
     textured
    0.39
     texte
    0.39
     TEXT
    0.39
    Act Density 0.000%

    No Known Activations