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

    Neuronpedia

    INDEX
    Explanations

    video

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     global
    -0.07
     zug
    -0.07
     Southern
    -0.07
     oste
    -0.06
     zwischen
    -0.06
    анием
    -0.06
    itz
    -0.06
     Theme
    -0.06
     عمومی
    -0.06
     severe
    -0.06
    POSITIVE LOGITS
     coleg
    0.07
    /'↵↵
    0.06
    _boolean
    0.06
    areth
    0.06
    ắ
    0.06
     >>↵↵
    0.06
    dept
    0.06
     pione
    0.06
    KERNEL
    0.06
     sheriff
    0.06
    Act Density 0.005%

    No Known Activations