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

    Neuronpedia

    INDEX
    Explanations

    leadership

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.89
    Autoritní
    -0.79
    water
    -0.75
     Leadership
    -0.73
     propOrder
    -0.69
     Drum
    -0.68
    허
    -0.66
    Personensuche
    -0.65
    Drum
    -0.64
    drum
    -0.63
    POSITIVE LOGITS
    ized
    0.52
    ic
    0.49
    клопе
    0.46
    ktur
    0.46
     Latimer
    0.45
    ised
    0.45
    万一
    0.45
    specialchars
    0.45
     Colony
    0.44
     Busy
    0.44
    Act Density 0.060%

    No Known Activations