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

    Neuronpedia

    INDEX
    Explanations

    level

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Если
    -0.06
    投資
    -0.06
    314
    -0.06
    AMY
    -0.06
    ォ
    -0.06
    aran
    -0.06
     servi
    -0.06
    robot
    -0.06
    .Magic
    -0.06
    proxy
    -0.05
    POSITIVE LOGITS
    (loc
    0.09
    数
    0.07
     residing
    0.07
     scripting
    0.07
     falsehood
    0.07
    changing
    0.07
    Exception
    0.07
    iddled
    0.07
    iddle
    0.07
    	Logger
    0.07
    Act Density 0.017%

    No Known Activations