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

    Neuronpedia

    INDEX
    Explanations

    Conversational sentences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Soon
    -0.06
     احمد
    -0.06
    -step
    -0.06
     Thorn
    -0.06
    ảnh
    -0.06
     позвол
    -0.06
     delt
    -0.06
    love
    -0.06
    cli
    -0.06
    _DELAY
    -0.06
    POSITIVE LOGITS
    Resize
    0.07
     okum
    0.07
     AB
    0.06
     teammate
    0.06
     вік
    0.06
    urent
    0.06
    らしい
    0.06
     Defaults
    0.06
     juxtap
    0.06
     comm
    0.06
    Act Density 0.171%

    No Known Activations