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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Base
    -0.06
    rch
    -0.06
    _SPELL
    -0.06
     teas
    -0.06
    gis
    -0.06
    <main
    -0.06
    χαν
    -0.06
     який
    -0.06
    (bean
    -0.06
    _main
    -0.06
    POSITIVE LOGITS
     retir
    0.07
    repr
    0.06
    esse
    0.06
    	opts
    0.06
    ламент
    0.06
    -def
    0.06
    })
↵
    0.06
    arrants
    0.06
     CPUs
    0.06
    fr
    0.06
    Act Density 0.496%

    No Known Activations