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

    Neuronpedia

    INDEX
    Explanations

    fire

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เหน
    -0.09
     cents
    -0.08
     lingü
    -0.08
    Glyph
    -0.07
     preparation
    -0.07
     fidél
    -0.07
     clown
    -0.07
    Preparation
    -0.07
     dime
    -0.07
    पूर्व
    -0.07
    POSITIVE LOGITS
    iptables
    0.13
     firewall
    0.12
     Firewall
    0.11
    Firewall
    0.11
     blockage
    0.11
    阻
    0.11
     blocking
    0.11
     Blocking
    0.10
    blocking
    0.10
     blockade
    0.10
    Act Density 0.008%

    No Known Activations