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

    Neuronpedia

    INDEX
    Explanations

    Toca Boca, tocopherol, tocino

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     patch
    0.39
     پل
    0.37
     Mit
    0.36
     sm
    0.35
    sou
    0.35
    plats
    0.35
    ቈ
    0.35
     squash
    0.34
     phase
    0.34
     connection
    0.34
    POSITIVE LOGITS
     ekspl
    0.42
    ᄊ
    0.41
     செய்வத
    0.40
     Toc
    0.39
    㖩
    0.39
     intens
    0.38
    cedure
    0.38
    enteuer
    0.38
    逪
    0.38
    TreeNavigator
    0.38
    Act Density 0.000%

    No Known Activations