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

    Neuronpedia

    INDEX
    Explanations

    People and roles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nil
    -0.07
    IVAL
    -0.07
    舗
    -0.07
    yps
    -0.06
     Imperial
    -0.06
     punch
    -0.06
     borne
    -0.06
    _Name
    -0.06
     pog
    -0.06
     Parl
    -0.06
    POSITIVE LOGITS
     يكون
    0.07
    [];↵
    0.07
     adress
    0.07
     син
    0.06
    modified
    0.06
    таб
    0.06
    "]->
    0.06
    there
    0.06
     λο
    0.06
     grands
    0.06
    Act Density 0.009%

    No Known Activations