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

    Neuronpedia

    INDEX
    Explanations

    tail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     epoxy
    -0.07
    赫
    -0.07
     santa
    -0.07
    例如
    -0.07
    ohen
    -0.07
    getBlock
    -0.07
    zo
    -0.07
     Všech
    -0.07
    ('=
    -0.06
     NRA
    -0.06
    POSITIVE LOGITS
     tail
    0.13
    tail
    0.10
     Tail
    0.10
    ail
    0.09
     trail
    0.09
    Tail
    0.09
     tails
    0.08
     Trail
    0.08
    ait
    0.08
    TAIL
    0.08
    Act Density 0.009%

    No Known Activations