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

    Neuronpedia

    INDEX
    Explanations

    Dichotomous Variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Serg
    -0.07
     Leicester
    -0.07
     Evelyn
    -0.06
     �
    -0.06
     mortal
    -0.06
     Jonathan
    -0.06
    _Map
    -0.06
     Curtain
    -0.06
    nego
    -0.06
     Deborah
    -0.06
    POSITIVE LOGITS
    ayers
    0.07
    bies
    0.07
     ###↵
    0.07
    browser
    0.07
    -android
    0.07
     patter
    0.06
     klub
    0.06
    PCM
    0.06
     χ
    0.06
     obst
    0.06
    Act Density 0.009%

    No Known Activations