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

    Neuronpedia

    INDEX
    Explanations

    toy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fry
    0.91
    Surely
    0.90
    当代
    0.89
     chill
    0.88
    Juven
    0.88
     illustrations
    0.85
     treks
    0.84
     Munch
    0.83
    Curs
    0.83
    Curso
    0.82
    POSITIVE LOGITS
     soldier
    1.37
     soldiers
    1.32
     soldados
    1.16
    士兵
    1.16
     Soldiers
    1.14
    zeug
    1.13
    otas
    1.09
     Soldier
    1.08
    box
    0.98
     soldado
    0.98
    Act Density 0.007%

    No Known Activations