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

    Neuronpedia

    INDEX
    Explanations

    animal tails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ipv
    -0.08
     qarşı
    -0.08
     opgelost
    -0.08
    -0.08
    Hosts
    -0.08
    IPs
    -0.07
     SYN
    -0.07
     survived
    -0.07
    ipmap
    -0.07
     grö
    -0.07
    POSITIVE LOGITS
    尾
    0.14
     tail
    0.13
    tail
    0.12
    -tail
    0.11
    Tail
    0.11
     tails
    0.11
    _tail
    0.11
     Schwanz
    0.10
    tails
    0.10
     trailing
    0.10
    Act Density 0.008%
    No Known Activations