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

    Neuronpedia

    INDEX
    Explanations

    Affected people / customers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seats
    -0.07
    .this
    -0.06
    Produto
    -0.06
    тим
    -0.06
    (Thread
    -0.06
     mensaje
    -0.06
    >{$
    -0.06
    掉
    -0.06
    。本
    -0.06
     matcher
    -0.06
    POSITIVE LOGITS
     Accessed
    0.07
    alarm
    0.06
     erken
    0.06
    (updated
    0.06
     innoc
    0.06
     bravery
    0.06
     야
    0.06
     chemical
    0.06
     samo
    0.06
     insn
    0.06
    Act Density 0.030%

    No Known Activations