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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Spoiler
    -0.07
     Cunningham
    -0.06
    POSITORY
    -0.06
    ίνη
    -0.06
    TI
    -0.06
    �
    -0.06
     Kop
    -0.06
    dık
    -0.06
     outpost
    -0.06
    ouser
    -0.06
    POSITIVE LOGITS
    点击
    0.07
    */↵
    0.07
    _SESSION
    0.07
    -enh
    0.07
     {[%
    0.07
    _decrypt
    0.07
     gradients
    0.06
    exit
    0.06
     preventing
    0.06
    容
    0.06
    Act Density 0.008%

    No Known Activations