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

    Neuronpedia

    INDEX
    Explanations

    movement and discussion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     étoient
    -0.80
     photolibrary
    -0.79
    UserScript
    -0.79
    -0.77
     étoit
    -0.75
    -£
    -0.75
    fjspx
    -0.75
     Wikimedijinoj
    -0.74
     RestTemplate
    -0.73
    berdayakan
    -0.73
    POSITIVE LOGITS
     the
    0.97
     our
    0.89
    <bos>
    0.84
     a
    0.82
     
    0.70
     that
    0.69
     one
    0.68
     The
    0.67
     this
    0.65
     some
    0.64
    Act Density 0.098%

    No Known Activations