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

    Neuronpedia

    INDEX
    Explanations

    VM, KVM, VS Code, iterators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    前辈
    0.49
     lé
    0.47
     ganar
    0.46
     val
    0.44
    ‖</
    0.44
     klasy
    0.44
    蝎
    0.44
     kwiet
    0.43
     veliko
    0.43
     onRouteChange
    0.43
    POSITIVE LOGITS
    mint
    0.49
     आहोत
    0.48
    Mint
    0.45
    وی
    0.45
    ",
    0.44
    food
    0.43
     entrusted
    0.42
     Mint
    0.42
     पाणी
    0.41
    mental
    0.41
    Act Density 0.001%

    No Known Activations