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

    Neuronpedia

    INDEX
    Explanations

    say "the ending db"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ob
    -0.07
     [[]
    -0.06
     ped
    -0.06
    .setLocation
    -0.06
    _register
    -0.06
     amazed
    -0.06
    ritic
    -0.06
    Zip
    -0.06
     contracts
    -0.06
    lian
    -0.06
    POSITIVE LOGITS
     Kirk
    0.07
     olm
    0.07
     optical
    0.07
    影
    0.06
    Experimental
    0.06
    _^
    0.06
     umožňuje
    0.06
    _graph
    0.06
    .unlock
    0.06
     联
    0.06
    Act Density 0.123%

    No Known Activations