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

    Neuronpedia

    INDEX
    Explanations

    may

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ich
    -0.06
    anager
    -0.06
    	op
    -0.06
    akers
    -0.06
    .clients
    -0.06
     너
    -0.06
    itlement
    -0.06
     �
    -0.06
     Operand
    -0.06
     Joel
    -0.06
    POSITIVE LOGITS
    gli
    0.07
     neural
    0.06
    423
    0.06
     legacy
    0.06
     MAY
    0.06
    殺
    0.06
    Mask
    0.06
     Approximately
    0.06
     mix
    0.06
    May
    0.06
    Act Density 0.005%

    No Known Activations