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

    Neuronpedia

    INDEX
    Explanations

    solubility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contemplate
    -0.07
    änner
    -0.07
    />.↵↵
    -0.07
    爷
    -0.07
     transformation
    -0.07
     Está
    -0.07
    _pr
    -0.07
    ﺬ
    -0.07
    🎩
    -0.07
     explain
    -0.06
    POSITIVE LOGITS
     CONT
    0.08
    kelig
    0.08
    บาง
    0.07
    чен
    0.07
    교육
    0.07
    _sq
    0.07
    ﻗ
    0.07
    igin
    0.07
    뷸
    0.07
    可怕
    0.07
    Act Density 0.006%

    No Known Activations