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

    Neuronpedia

    INDEX
    Explanations

    say ".io"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -arrow
    -0.07
     dicho
    -0.07
    ätzlich
    -0.06
     Drivers
    -0.06
    纹
    -0.06
     actor
    -0.06
    .addElement
    -0.06
    uestas
    -0.06
    מקומות
    -0.06
    瞄
    -0.06
    POSITIVE LOGITS
     ../../
    0.07
     semiclassical
    0.07
    的能量
    0.07
    קידום
    0.06
    _met
    0.06
    (factory
    0.06
    ейств
    0.06
    _expire
    0.06
    (rv
    0.06
     rejection
    0.06
    Act Density 0.001%

    No Known Activations