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

    Neuronpedia

    INDEX
    Explanations

    Russian programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -shirt
    -0.07
     spins
    -0.07
    -read
    -0.07
    shirt
    -0.07
    '},
↵
    -0.06
     Nachricht
    -0.06
     Canon
    -0.06
    rangle
    -0.06
     holder
    -0.06
    .review
    -0.06
    POSITIVE LOGITS
     мі
    0.07
    nictvím
    0.07
    ISTS
    0.07
     AVR
    0.06
    ($.
    0.06
    _hosts
    0.06
     Hero
    0.06
     '&'
    0.06
    -gl
    0.06
    ANCE
    0.06
    Act Density 0.127%

    No Known Activations