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

    Neuronpedia

    INDEX
    Explanations

    hiking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atican
    -0.07
    ”).
    -0.07
     jealousy
    -0.07
     fluids
    -0.07
    tell
    -0.07
     modal
    -0.06
    _contract
    -0.06
    Instant
    -0.06
     Deliver
    -0.06
    flake
    -0.06
    POSITIVE LOGITS
     hiking
    0.12
     hike
    0.09
     hikes
    0.08
    <Renderer
    0.08
     Üç
    0.07
    Kansas
    0.07
     Fen
    0.07
     Trek
    0.07
     birik
    0.07
    .Failure
    0.06
    Act Density 0.008%

    No Known Activations