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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	box
    -0.07
     onClose
    -0.07
    uffix
    -0.07
    --,
    -0.06
    طح
    -0.06
     switched
    -0.06
     SWITCH
    -0.06
     osoby
    -0.06
    ={`${
    -0.06
    559
    -0.06
    POSITIVE LOGITS
    VT
    0.08
     среди
    0.07
    openh
    0.07
     '>
    0.07
    reuse
    0.07
    iv
    0.07
    lista
    0.07
    ूष
    0.07
    vt
    0.06
    йн
    0.06
    Act Density 0.007%

    No Known Activations