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

    Neuronpedia

    INDEX
    Explanations

    Prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ITV
    -0.07
     builders
    -0.06
    ansa
    -0.06
     Tell
    -0.06
     marriages
    -0.06
    DELETE
    -0.06
    _Header
    -0.06
     Sunday
    -0.06
    냐
    -0.06
     인증
    -0.06
    POSITIVE LOGITS
     τι
    0.06
     AudioSource
    0.06
    ridden
    0.06
    .accel
    0.06
     وقد
    0.06
     ошиб
    0.06
     declaración
    0.06
     лог
    0.06
    яви
    0.06
     scoring
    0.06
    Act Density 0.085%

    No Known Activations