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

    Neuronpedia

    INDEX
    Explanations

    numbers and y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gene
    0.46
     elementos
    0.43
    élite
    0.41
    首先
    0.40
     atores
    0.40
     elemento
    0.39
    aloko
    0.38
    snapshots
    0.38
     deliberately
    0.37
    ;|&
    0.37
    POSITIVE LOGITS
    
    0.44
     diagonalization
    0.43
     ہزار
    0.38
     القرآن
    0.37
     विहार
    0.37
     पंजाबी
    0.37
    ہور
    0.37
    ☀️
    0.36
     ?$
    0.36
     Hayden
    0.36
    Act Density 0.002%

    No Known Activations