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

    Neuronpedia

    INDEX
    Explanations

    quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     photon
    -0.06
     فقد
    -0.06
    Destructor
    -0.06
     spoilers
    -0.06
    ̆
    -0.06
    mail
    -0.06
    αιο
    -0.06
    RL
    -0.06
    顾
    -0.06
    eth
    -0.06
    POSITIVE LOGITS
    389
    0.08
    _UNITS
    0.07
     courses
    0.06
     erm
    0.06
    ampion
    0.06
     Compar
    0.06
     complexes
    0.06
     inter
    0.06
    647
    0.06
     Voj
    0.06
    Act Density 0.048%

    No Known Activations