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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     instructor
    -0.07
     من
    -0.06
     Gemini
    -0.06
     extortion
    -0.06
    .strictEqual
    -0.06
    >Password
    -0.06
     continuum
    -0.06
     Moderator
    -0.06
     kitchen
    -0.06
     employees
    -0.06
    POSITIVE LOGITS
    465
    0.07
    Italy
    0.07
     mote
    0.06
    .htm
    0.06
    *',
    0.06
    _TYP
    0.06
     darn
    0.06
    《
    0.06
    .sha
    0.06
    ORDER
    0.06
    Act Density 0.003%

    No Known Activations