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

    Neuronpedia

    INDEX
    Explanations

    singular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     下午
    -0.07
    Execute
    -0.07
     Logout
    -0.06
    aturday
    -0.06
    clf
    -0.06
    -root
    -0.06
    GetInt
    -0.06
    _Delay
    -0.06
    amment
    -0.06
     improvis
    -0.06
    POSITIVE LOGITS
     singular
    0.18
     Singular
    0.13
    singular
    0.13
    ingular
    0.11
    676
    0.07
     solely
    0.07
    }`);↵
    0.07
     KR
    0.07
     battleground
    0.07
    loud
    0.07
    Act Density 0.001%

    No Known Activations