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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =L
    -0.06
    slug
    -0.06
     Lightning
    -0.06
     рад
    -0.06
    .fore
    -0.06
     ек
    -0.06
     серед
    -0.06
    _THAT
    -0.06
    -vector
    -0.06
    cooldown
    -0.06
    POSITIVE LOGITS
     потол
    0.07
    ObjectName
    0.06
     insn
    0.06
     призна
    0.06
    нівер
    0.06
     ballet
    0.06
     cherish
    0.06
    ());
↵
    0.06
    EventArgs
    0.06
    اغ
    0.06
    Act Density 0.039%

    No Known Activations