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

    Neuronpedia

    INDEX
    Explanations

    companies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	delete
    -0.07
    (api
    -0.06
    oters
    -0.06
    ["@
    -0.06
    successful
    -0.06
    Mur
    -0.06
    -large
    -0.06
     discord
    -0.06
     Bour
    -0.06
     Colour
    -0.06
    POSITIVE LOGITS
    .getParam
    0.07
    _sr
    0.07
     педагог
    0.07
    _PART
    0.07
    straints
    0.06
     gubern
    0.06
    _KERNEL
    0.06
     psychiatric
    0.06
     births
    0.06
    cales
    0.06
    Act Density 0.004%

    No Known Activations