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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lao
    -0.07
    Integrated
    -0.07
    irc
    -0.06
     microbes
    -0.06
    hall
    -0.06
    >(),
    -0.06
    ण
    -0.06
     tables
    -0.06
    ايات
    -0.06
    Red
    -0.06
    POSITIVE LOGITS
     tempt
    0.06
     setId
    0.06
     después
    0.06
    _COMMIT
    0.06
    ITT
    0.06
    iciary
    0.06
     referencing
    0.06
    BERS
    0.06
    Extras
    0.06
     puis
    0.06
    Act Density 0.108%

    No Known Activations