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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    へ
    -0.07
     Savannah
    -0.07
    .connected
    -0.06
    до
    -0.06
    _WINDOWS
    -0.06
    .array
    -0.06
    gregated
    -0.06
    (nn
    -0.06
     원
    -0.06
    vailable
    -0.06
    POSITIVE LOGITS
    plain
    0.06
     stu
    0.06
     ){↵↵
    0.06
    Transfer
    0.06
     lies
    0.06
    养
    0.06
     lying
    0.06
    _objs
    0.06
    	puts
    0.06
    σσ
    0.06
    Act Density 0.012%

    No Known Activations