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

    Neuronpedia

    INDEX
    Explanations

    study aims

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SIMPLE
    -0.07
    _layers
    -0.07
     Allies
    -0.06
    ===========
    -0.06
    　　　　　 　
    -0.06
    eny
    -0.06
    ]),
    -0.06
    �y
    -0.06
     Conway
    -0.06
     Doctors
    -0.06
    POSITIVE LOGITS
    �
    0.07
    める
    0.07
     основі
    0.07
     overseeing
    0.07
     liking
    0.06
     rtn
    0.06
     backup
    0.06
    rawer
    0.06
     Прот
    0.06
    three
    0.06
    Act Density 0.059%

    No Known Activations