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

    Neuronpedia

    INDEX
    Explanations

    encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    trigger
    -0.07
    xcc
    -0.07
     stolen
    -0.07
    enna
    -0.07
     prog
    -0.07
     spawn
    -0.07
    _Total
    -0.07
     shells
    -0.07
    adena
    -0.07
    辰
    -0.06
    POSITIVE LOGITS
    icontains
    0.07
    드는
    0.06
     میک
    0.06
    communications
    0.06
     ох
    0.06
     splendid
    0.06
    (&_
    0.06
     تشکیل
    0.05
    오는
    0.05
     о
    0.05
    Act Density 0.001%

    No Known Activations