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

    Neuronpedia

    INDEX
    Explanations

    `

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    стить
    -0.98
    火影
    -0.92
    どちら
    -0.92
    CCIÓN
    -0.91
    regler
    -0.90
    REFRESH
    -0.88
     Obwohl
    -0.85
    StringTo
    -0.85
    redning
    -0.84
    loginButton
    -0.84
    POSITIVE LOGITS
    lateinit
    0.81
    针对
    0.81
     Âge
    0.81
    never
    0.80
     osp
    0.79
    πι
    0.78
    П
    0.77
    ↦
    0.77
     ermöglicht
    0.77
     here
    0.76
    Act Density 0.021%

    No Known Activations