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

    Neuronpedia

    INDEX
    Explanations

    type checking `typeof`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    с
    0.85
    it
    0.65
    قية
    0.65
    opia
    0.65
     MOT
    0.64
     Period
    0.63
     Diss
    0.60
    ante
    0.60
    oltre
    0.59
    സ്യ
    0.59
    POSITIVE LOGITS
    璐
    0.81
    órios
    0.80
    ತ್ರಿ
    0.79
    য়
    0.79
    μών
    0.78
     puppets
    0.78
    ｒ
    0.78
    ดังกล่าว
    0.78
    पछि
    0.77
     thieves
    0.76
    Act Density 0.001%

    No Known Activations