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

    Neuronpedia

    INDEX
    Explanations

    say ","

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sensor
    -0.08
     puzzle
    -0.07
    军
    -0.07
    _quit
    -0.07
    /win
    -0.07
     diz
    -0.07
    olas
    -0.06
    _encrypt
    -0.06
     reactor
    -0.06
     Mushroom
    -0.06
    POSITIVE LOGITS
    .hy
    0.06
    }.${
    0.06
     rip
    0.06
     рез
    0.06
    Meeting
    0.06
     Fluent
    0.06
     业
    0.06
     Rip
    0.06
    umatic
    0.06
    516
    0.05
    Act Density 0.220%

    No Known Activations