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

    Neuronpedia

    INDEX
    Explanations

    truncate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     solver
    -0.07
     Simon
    -0.07
    发送
    -0.07
     blends
    -0.06
    ýval
    -0.06
     yy
    -0.06
    worked
    -0.06
     excell
    -0.06
    Those
    -0.06
    Besides
    -0.06
    POSITIVE LOGITS
     trunc
    0.10
    truncate
    0.09
     truncate
    0.08
     truncated
    0.08
    .ca
    0.07
    _TRUNC
    0.07
    uke
    0.07
    hoe
    0.07
    uncated
    0.07
     Ac
    0.07
    Act Density 0.002%

    No Known Activations