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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     production
    -0.07
    (expression
    -0.07
    stype
    -0.07
     plastics
    -0.07
     stretch
    -0.06
     interceptor
    -0.06
    Trash
    -0.06
     ent
    -0.06
     Lance
    -0.06
    _structure
    -0.06
    POSITIVE LOGITS
    asz
    0.07
    ंग
    0.07
    ρει
    0.06
    PropertyParams
    0.06
    ='',
    0.06
    Pk
    0.06
    Eliminar
    0.06
    Nuitka
    0.06
    	HX
    0.06
    =back
    0.06
    Act Density 0.029%

    No Known Activations