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

    Neuronpedia

    INDEX
    Explanations

    battleships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	option
    -0.07
    _yield
    -0.07
     requests
    -0.06
    377
    -0.06
    _BIND
    -0.06
     Requests
    -0.06
     Rae
    -0.06
     gases
    -0.06
     coment
    -0.06
     commands
    -0.06
    POSITIVE LOGITS
    Benef
    0.06
     ува
    0.06
    Jimmy
    0.06
     FontStyle
    0.06
     süresi
    0.06
     benchmark
    0.06
    .FontStyle
    0.06
     workload
    0.06
     objectAtIndex
    0.05
     Ї
    0.05
    Act Density 0.105%

    No Known Activations