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

    Neuronpedia

    INDEX
    Explanations

    walls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sub
    -0.07
    卢
    -0.07
     concatenated
    -0.06
     Sanders
    -0.06
    犯
    -0.06
     تق
    -0.06
    563
    -0.06
    .week
    -0.06
     başladı
    -0.06
    ndef
    -0.06
    POSITIVE LOGITS
     firewall
    0.09
     Firewall
    0.08
    _TRANSFER
    0.07
     detalle
    0.07
    ):
    0.07
    0.07
    Latest
    0.07
    NECTION
    0.07
    ittel
    0.07
     firepower
    0.07
    Act Density 0.006%

    No Known Activations