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

    Neuronpedia

    INDEX
    Explanations

    Manuals and parts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FML
    -0.07
     Savior
    -0.07
     vidět
    -0.07
    ζη
    -0.07
    。そして
    -0.07
     ze
    -0.06
    าส
    -0.06
     воз
    -0.06
     hollow
    -0.06
    壓
    -0.06
    POSITIVE LOGITS
    leshooting
    0.07
     sentences
    0.07
     models
    0.06
    ={}
    0.06
     تمامی
    0.06
    Sometimes
    0.06
    -ending
    0.06
     Models
    0.06
    Allocate
    0.06
    COMMENT
    0.06
    Act Density 0.019%

    No Known Activations