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

    Neuronpedia

    INDEX
    Explanations

    abide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Swords
    -0.07
    距离
    -0.07
    距離
    -0.07
    candidates
    -0.06
    Lists
    -0.06
    CASCADE
    -0.06
     '../../
    -0.06
    具有
    -0.06
    цуз
    -0.06
    _JS
    -0.06
    POSITIVE LOGITS
     abide
    0.13
     Wohn
    0.06
     xuyên
    0.06
     �
    0.06
    �
    0.06
    いか
    0.06
     isten
    0.06
     JNIEnv
    0.06
    _es
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations