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

    Neuronpedia

    INDEX
    Explanations

    calculus and mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }={
    0.57
    Под
    0.53
    HCl
    0.52
    มั่น
    0.50
    }());
    0.49
    APS
    0.49
    }");
    0.49
     жок
    0.48
    ⋮
    0.48
    encoding
    0.48
    POSITIVE LOGITS
     实现
    0.53
    的东西
    0.51
     otra
    0.51
     /(\
    0.49
    옮
    0.49
     用于
    0.49
     contributions
    0.48
     ration
    0.48
     recoger
    0.47
     ای
    0.47
    Act Density 0.036%

    No Known Activations