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

    Neuronpedia

    INDEX
    Explanations

    could ever

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "</
    -0.07
     SYSTEM
    -0.06
    Smooth
    -0.06
    کنون
    -0.06
     QT
    -0.06
     ACL
    -0.06
     Pivot
    -0.06
    редел
    -0.06
    ovenant
    -0.06
    ="/
    -0.06
    POSITIVE LOGITS
    cmb
    0.07
    σιο
    0.07
    /mail
    0.07
    Capacity
    0.06
     alk
    0.06
    줄
    0.06
    数学
    0.06
    투
    0.06
    \"",
    0.06
    �
    0.06
    Act Density 0.044%

    No Known Activations