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

    Neuronpedia

    INDEX
    Explanations

    remaining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
    Tap
    -0.06
     critics
    -0.06
     helmets
    -0.06
    peq
    -0.06
     publishers
    -0.06
    Provides
    -0.06
    };
↵
    -0.06
     eager
    -0.05
    iteral
    -0.05
    POSITIVE LOGITS
    .FragmentManager
    0.07
     فراو
    0.07
     american
    0.07
    جاد
    0.06
    fail
    0.06
     cré
    0.06
    _Tr
    0.06
    067
    0.06
     (?
    0.06
    (project
    0.06
    Act Density 0.013%

    No Known Activations