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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hosts
    -0.07
    icipant
    -0.07
    _heat
    -0.06
     Hunt
    -0.06
    990
    -0.06
    >\<
    -0.06
    DEC
    -0.06
    Map
    -0.06
     fascinating
    -0.06
     Host
    -0.06
    POSITIVE LOGITS
     Zombie
    0.07
    려고
    0.06
    承
    0.06
    ρος
    0.06
     الأد
    0.06
     گیری
    0.06
     设置
    0.06
    さんは
    0.06
    getIndex
    0.06
    通常
    0.06
    Act Density 0.055%

    No Known Activations