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

    Neuronpedia

    INDEX
    Explanations

    Council

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.59
     protoimpl
    -0.56
    gica
    -0.54
    исленность
    -0.53
    mű
    -0.50
    InputBorder
    -0.48
    craft
    -0.47
    obacterium
    -0.46
    pere
    -0.46
    ysty
    -0.46
    POSITIVE LOGITS
    PyExc
    0.72
     nakalista
    0.57
     souls
    0.54
     referenties
    0.54
     Stops
    0.52
     חיצוניים
    0.51
    styleUrls
    0.51
     masses
    0.50
     Controllers
    0.50
    bungen
    0.50
    Act Density 0.016%

    No Known Activations