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

    Neuronpedia

    INDEX
    Explanations

    choice label B

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tastes
    0.42
     sensual
    0.40
     mutagen
    0.38
     variants
    0.37
     RAX
    0.37
    ALI
    0.36
     anytime
    0.36
     dab
    0.36
    irao
    0.36
     degrees
    0.35
    POSITIVE LOGITS
     C
    0.37
    ционных
    0.36
    ussch
    0.35
    khar
    0.34
    емых
    0.33
    ünden
    0.33
    ktions
    0.33
    iane
    0.33
    डाय
    0.33
    setC
    0.33
    Act Density 0.014%

    No Known Activations