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

    Neuronpedia

    INDEX
    Explanations

    medical testing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Msg
    -0.08
    Ops
    -0.07
    Atom
    -0.07
    WRITE
    -0.07
    Fil
    -0.06
    	String
    -0.06
    That
    -0.06
    Format
    -0.06
    ]:
    -0.06
     tomorrow
    -0.06
    POSITIVE LOGITS
    вищ
    0.06
     jednotlivých
    0.06
     totalmente
    0.06
     worldly
    0.06
     xv
    0.06
    'B
    0.06
    -hard
    0.06
     Desde
    0.06
     às
    0.06
     опред
    0.06
    Act Density 0.033%

    No Known Activations