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

    Neuronpedia

    INDEX
    Explanations

    lyrics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Specifies
    -0.07
     Specify
    -0.07
     SHOW
    -0.07
    widget
    -0.07
    绍
    -0.07
    _BLOCKS
    -0.06
     doubts
    -0.06
    SIGN
    -0.06
    ustry
    -0.06
    Okay
    -0.06
    POSITIVE LOGITS
    round
    0.08
     lớp
    0.07
     imprisonment
    0.07
     mieszkań
    0.07
     mennes
    0.07
     filtering
    0.07
    短板
    0.06
     федеральн
    0.06
     Scarlet
    0.06
     의원
    0.06
    Act Density 0.009%

    No Known Activations