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

    Neuronpedia

    INDEX
    Explanations

    root

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tenía
    -0.06
    .reward
    -0.06
    як
    -0.06
    greSQL
    -0.06
    ,module
    -0.06
     घटन
    -0.06
     ceramics
    -0.06
    _performance
    -0.06
    _DIS
    -0.06
    abilidad
    -0.06
    POSITIVE LOGITS
     newPassword
    0.07
    anonymous
    0.07
    rou
    0.07
    õ
    0.06
     Zip
    0.06
     unk
    0.06
    (U
    0.06
    hil
    0.06
    ераль
    0.06
    991
    0.06
    Act Density 0.009%

    No Known Activations