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

    Neuronpedia

    INDEX
    Explanations

    knowledge/acknowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .matrix
    -0.07
    .fasta
    -0.07
     四
    -0.07
     tempList
    -0.07
     LSU
    -0.07
    fruit
    -0.07
    354
    -0.07
    paste
    -0.07
    _TEMP
    -0.07
     Bent
    -0.07
    POSITIVE LOGITS
     Ack
    0.09
     acknowled
    0.08
    Ack
    0.07
     enclave
    0.07
     acknowledges
    0.07
     acknowledge
    0.07
     acknowledged
    0.07
    奉
    0.07
     acknowledging
    0.07
     grateful
    0.07
    Act Density 0.005%

    No Known Activations