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

    Neuronpedia

    INDEX
    Explanations

    D

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    稳妥
    -0.07
     DLC
    -0.07
    Android
    -0.07
     UnsupportedOperationException
    -0.06
    佺
    -0.06
    เทคโน
    -0.06
    waukee
    -0.06
    文创
    -0.06
    НО
    -0.06
    throp
    -0.06
    POSITIVE LOGITS
     DEFIN
    0.08
    യ
    0.08
    后
    0.07
     //.
    0.07
    ending
    0.07
     raising
    0.07
    خروج
    0.07
    Alternatively
    0.07
    电路
    0.06
    "A
    0.06
    Act Density 0.372%

    No Known Activations