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

    Neuronpedia

    INDEX
    Explanations

    He's gonna / He is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nder
    0.40
    ysz
    0.40
    preuve
    0.39
    azas
    0.38
    Payroll
    0.38
    ella
    0.37
    ylabel
    0.37
    ալ
    0.37
    retien
    0.37
    baz
    0.37
    POSITIVE LOGITS
    UserModel
    0.40
     nacido
    0.39
     AGEN
    0.39
     born
    0.38
     blossomed
    0.37
     character
    0.37
     satu
    0.37
    })(
    0.37
     lif
    0.36
     deserving
    0.36
    Act Density 0.000%

    No Known Activations