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

    Neuronpedia

    INDEX
    Explanations

    tongue or ue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     counts
    -0.07
    ("@
    -0.07
    059
    -0.06
     isol
    -0.06
    適
    -0.06
     Bin
    -0.06
     beled
    -0.06
    "Just
    -0.06
     Mineral
    -0.06
    났
    -0.06
    POSITIVE LOGITS
     tongue
    0.20
     tongues
    0.15
     Tong
    0.12
     Dragon
    0.07
     tipping
    0.07
     tong
    0.07
    ког
    0.07
     tooth
    0.07
     ENGINE
    0.06
     �
    0.06
    Act Density 0.004%

    No Known Activations