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

    Neuronpedia

    INDEX
    Explanations

    command

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     command
    -1.13
    command
    -0.82
    Cooling
    -0.75
     Cooling
    -0.70
     Command
    -0.69
     comando
    -0.66
    BufferException
    -0.64
     cooling
    -0.63
     الرياضيه
    -0.58
    cooling
    -0.57
    POSITIVE LOGITS
    s
    0.60
     invokingState
    0.59
    migrationBuilder
    0.57
    a
    0.57
     centers
    0.55
     Egli
    0.52
    Eloquent
    0.51
    ی
    0.50
     disponibilités
    0.48
    setVerticalGroup
    0.48
    Act Density 0.163%

    No Known Activations