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

    Neuronpedia

    INDEX
    Explanations

    firewall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     valore
    -0.07
    년도
    -0.07
    :"+
    -0.07
     ASE
    -0.06
     lista
    -0.06
    addtogroup
    -0.06
     genuinely
    -0.06
    _RSA
    -0.06
    uta
    -0.06
     نمود
    -0.06
    POSITIVE LOGITS
     manually
    0.07
    .Reset
    0.07
     firewall
    0.07
    .ir
    0.07
    wall
    0.06
    ATCH
    0.06
    _sep
    0.06
     settling
    0.06
     checker
    0.06
    loom
    0.06
    Act Density 0.004%

    No Known Activations