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

    Neuronpedia

    INDEX
    Explanations

    changing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pd
    -0.07
     glean
    -0.07
     tarafından
    -0.07
     ***
    -0.07
    iec
    -0.07
    OrNull
    -0.07
    _CONTINUE
    -0.07
    -producing
    -0.07
    ksz
    -0.07
     theoretical
    -0.06
    POSITIVE LOGITS
    plr
    0.07
    跟
    0.07
    簡
    0.06
     Emb
    0.06
    �
    0.06
    长短
    0.06
    不清
    0.06
    到处
    0.06
    stackpath
    0.06
     frameworks
    0.06
    Act Density 0.007%

    No Known Activations