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

    Neuronpedia

    INDEX
    Explanations

    Colon character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Century
    -0.06
     срок
    -0.06
    -0.06
    mtx
    -0.06
     Это
    -0.06
    NSAttributedString
    -0.06
     ripe
    -0.06
     ck
    -0.06
    ]='
    -0.06
     Sting
    -0.06
    POSITIVE LOGITS
     sealed
    0.07
    .(
    0.07
    -m
    0.07
     pretending
    0.06
    cuador
    0.06
     letting
    0.06
     избав
    0.06
     thermometer
    0.06
    .payload
    0.06
     try
    0.06
    Act Density 0.001%

    No Known Activations