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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ності
    -0.07
     constellation
    -0.07
    hibited
    -0.06
    panic
    -0.06
    ')}}"
    -0.06
    iversite
    -0.06
    ностей
    -0.06
    ёл
    -0.06
    .assertFalse
    -0.06
    AGO
    -0.06
    POSITIVE LOGITS
     жест
    0.06
    致
    0.06
     thems
    0.06
    	vm
    0.06
     hack
    0.06
    सन
    0.06
    /umd
    0.06
    鼓
    0.06
    ltra
    0.05
     Συν
    0.05
    Act Density 0.000%

    No Known Activations