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

    Neuronpedia

    INDEX
    Explanations

    virtual environments, python

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ',{↵
    -0.08
    502
    -0.07
     instantiated
    -0.07
     bastante
    -0.07
    -metal
    -0.06
    {};↵
    -0.06
    =#{
    -0.06
    587
    -0.06
    benchmark
    -0.06
    -0.06
    POSITIVE LOGITS
     rent
    0.07
    登录
    0.07
    vid
    0.07
    忍
    0.06
    _ord
    0.06
     lar
    0.06
    applicant
    0.06
     hodin
    0.06
    Personal
    0.06
     Sass
    0.06
    Act Density 0.016%

    No Known Activations